© 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. 2312
    Prev
    Next
    INDEX
    Explanations

    scientific terms related to environmental and biological responses

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

    technical and academic language with scientific terminology and formal scholarly discourse.

    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
    Lots
    -0.56
     people
    -0.55
    いろいろな
    -0.53
     lots
    -0.52
     everybody
    -0.52
     différent
    -0.52
     because
    -0.51
     diferente
    -0.49
     Everybody
    -0.48
    Different
    -0.48
    POSITIVE LOGITS
    AutoScaleMode
    0.89
     kasarigan
    0.83
    rungsseite
    0.82
    已然
    0.81
    这般
    0.80
     pungkas
    0.79
    IsMutable
    0.78
     requisite
    0.73
    AsUp
    0.73
     nonché
    0.72
    Activations Density 8.939%

    No Known Activations