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

    Neuronpedia

    APICircuit 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. 5-GEMMASCOPE-RES-16K
    6. 1519
    Prev
    Next
    INDEX
    Explanations

    structural and formatting elements in data or code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     linkovi
    -0.66
    wapV
    -0.59
    |}{}
    -0.56
    bibinfo
    -0.55
    theid
    -0.54
    (")");
    -0.53
    bibnamefont
    -0.52
    routed
    -0.52
     userSchema
    -0.51
     tela
    -0.51
    POSITIVE LOGITS
    MigrationBuilder
    0.62
    mirante
    0.58
    intios
    0.57
    awtextra
    0.57
     francès
    0.57
    ValueStyle
    0.56
     noires
    0.55
     nhau
    0.55
     AssemblyCompany
    0.54
     niyang
    0.54
    Activations Density 0.616%

    No Known Activations