© 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. 3764
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases related to professional achievement and performance metrics

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

    numerical values and quantitative data points in text.

    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
     velkommen
    -0.43
    CloseOperation
    -0.41
     daarom
    -0.39
    可以直接
    -0.38
     "..\..\
    -0.37
     proviene
    -0.37
    Поэтому
    -0.37
     precede
    -0.36
    WEBPACK
    -0.36
     Поэтому
    -0.36
    POSITIVE LOGITS
     taking
    1.16
     bringing
    1.13
     preferring
    1.08
     используя
    1.05
     giving
    1.04
     making
    1.02
     using
    1.02
     leaving
    1.00
     adding
    1.00
     believing
    0.99
    Activations Density 0.932%

    No Known Activations