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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 14414
    Prev
    Next
    INDEX
    Explanations

    terminology related to financial liability and insurance

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

    Word following "is", "are", "holds", or "comes"

    np_acts-logits-general · gemini-2.0-flash

    member or affiliation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.90
    IVEREF
    -0.83
    AndEndTag
    -0.81
    Personendaten
    -0.81
     Walkover
    -0.80
    MigrationBuilder
    -0.79
     ExecuteAsync
    -0.72
     дописавши
    -0.72
    EndGlobalSection
    -0.70
    awtextra
    -0.68
    POSITIVE LOGITS
     BBB
    0.69
     Better
    0.61
    Demografia
    0.55
    MEMBER
    0.54
     member
    0.53
    BBB
    0.52
    Better
    0.52
    Lic
    0.51
     affiliations
    0.51
     Lic
    0.50
    Activations Density 0.119%

    No Known Activations