© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 6426
    Prev
    Next
    INDEX
    Explanations

    approaches and methods in technical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    sentences describing methodological or procedural approaches to solving problems.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou

    phrases introducing technical methods, approaches, or solutions in explanatory or instructional contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    sentences that present and evaluate a specific technical approach or method, often with modal qualifiers and references to earlier content.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rungsseite
    -0.72
     betweenstory
    -0.61
    bootstrapcdn
    -0.58
    󠁴
    -0.52
    PerformLayout
    -0.52
     Signalez
    -0.50
     חיצוניים
    -0.49
     består
    -0.48
    는데
    -0.48
     acompaña
    -0.47
    POSITIVE LOGITS
     avoids
    0.52
     eliminates
    0.51
     disadvantages
    0.50
     advantages
    0.48
     loses
    0.46
     solves
    0.46
     minimizes
    0.45
     yields
    0.45
     avoid
    0.43
     sounds
    0.43
    Activations Density 1.100%

    No Known Activations