© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 16179
    Prev
    Next
    INDEX
    Explanations

    phrases related to food and its representation in context

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

    commas that separate independent clauses or list items in longer sentences.

    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
     AssemblyCompany
    -0.72
     BaseActivity
    -0.55
    MessageOf
    -0.44
    AndEndTag
    -0.44
    mappedBy
    -0.44
    InjectAttribute
    -0.41
    HtmlAttribute
    -0.40
     transférez
    -0.40
    دانشنامهٔ
    -0.39
    ngrx
    -0.39
    POSITIVE LOGITS
     there
    0.90
    there
    0.65
     we
    0.57
     everyone
    0.56
     eikä
    0.56
     theres
    0.55
     people
    0.49
     everybody
    0.49
    There
    0.49
    everyone
    0.47
    Activations Density 0.542%

    No Known Activations