© 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. 14785
    Prev
    Next
    INDEX
    Explanations

    terms related to data management and systems usage

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

    words that frequently appear in sequences describing common experiences or situations across diverse contexts.

    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
     eigentlichen
    -0.43
    Really
    -0.40
     nữa
    -0.40
    Sudden
    -0.39
     really
    -0.39
     might
    -0.37
    反而
    -0.36
    Perhaps
    -0.36
     perhaps
    -0.36
    逆に
    -0.36
    POSITIVE LOGITS
     atleast
    1.25
     almeno
    1.25
     algún
    1.23
     irgende
    1.22
     alguna
    1.21
     algum
    1.19
     somewhere
    1.16
    至少
    1.13
     alguma
    1.11
    somewhere
    1.10
    Activations Density 1.013%

    No Known Activations