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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 10673
    Prev
    Next
    INDEX
    Explanations

    elements related to color specifications in coding or programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    ItemBackground
    -0.47
    inetto
    -0.45
    bcryptjs
    -0.45
    mbang
    -0.43
    ائم
    -0.41
    Życiorys
    -0.41
     Lauter
    -0.40
     correctes
    -0.40
    JsonPropertyName
    -0.40
    white
    -0.39
    POSITIVE LOGITS
    httphttps
    0.82
    +#+
    0.75
    rrggbb
    0.74
    routeProvider
    0.66
    #
    0.63
     мәкал
    0.62
    PointerException
    0.60
    BufferException
    0.60
    cessive
    0.60
     déclaration
    0.59
    Activations Density 0.095%

    No Known Activations