Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 9085
    Prev
    Next
    INDEX
    Explanations

    references to psychological issues and interpersonal struggles

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

    phrases expressing struggle, hardship, or difficult challenges that individuals have to overcome.

    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
    évaluateur
    -0.48
     AssemblyCulture
    -0.47
     löyty
    -0.47
    complexContent
    -0.46
     Absicht
    -0.45
    enumii
    -0.43
     contextLoads
    -0.43
    outSlope
    -0.43
    awtextra
    -0.43
    __*/
    -0.42
    POSITIVE LOGITS
     dealing
    1.84
     Dealing
    1.64
    Dealing
    1.58
    dealing
    1.52
     deal
    1.52
     dealt
    1.44
     DEAL
    1.36
    deal
    1.33
     deals
    1.28
     Deal
    1.28
    Activations Density 0.461%

    No Known Activations