© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 8072
    Prev
    Next
    INDEX
    Explanations

    references to personal beliefs or social issues

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

    words and phrases that are semantically central or defining to the main topic being discussed.

    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
    accompanied
    -0.48
     bertujuan
    -0.38
     accompanied
    -0.38
    ells
    -0.35
    requires
    -0.35
     Таким
    -0.34
    known
    -0.34
    identified
    -0.34
    ands
    -0.33
    ết
    -0.33
    POSITIVE LOGITS
     being
    1.68
    being
    1.31
     BEING
    1.22
    Being
    1.13
     étant
    1.09
     becoming
    1.04
     Being
    1.02
     sendo
    0.97
     having
    0.93
     fiind
    0.92
    Activations Density 0.650%

    No Known Activations