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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 492
    Prev
    Next
    INDEX
    Explanations

    scientific studies that examine various aspects of treatment effects and research methods

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

    academic research paper introductions and methodology sections.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    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
    principalColumn
    -0.38
     StatefulWidget
    -0.35
    MergeFrom
    -0.34
     básicamente
    -0.31
    loggen
    -0.31
     zanah
    -0.30
    felizmente
    -0.30
    jména
    -0.30
     uzman
    -0.30
     semuanya
    -0.29
    POSITIVE LOGITS
     effect
    1.30
     effects
    1.27
     influence
    1.23
     Effect
    1.21
    Effect
    1.16
     Influence
    1.14
     Effects
    1.13
     impact
    1.13
    Influence
    1.09
    effect
    1.09
    Activations Density 1.910%

    No Known Activations