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. 16-GEMMASCOPE-RES-16K
    6. 6385
    Prev
    Next
    INDEX
    Explanations

    programming syntax and constructs

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

    Paired punctuation or symbols

    np_acts-logits-general · gemini-2.0-flash

    mathematical/programming symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    e
    -0.96
    i
    -0.92
     
    -0.89
    l
    -0.87
    S
    -0.85
    k
    -0.84
    K
    -0.84
     K
    -0.83
    y
    -0.82
    E
    -0.81
    POSITIVE LOGITS
     myſelf
    1.80
     Jefus
    1.68
    ſelves
    1.61
     pleaſure
    1.59
     themſelves
    1.57
     uſed
    1.56
     himſelf
    1.56
     Theſe
    1.55
     itſelf
    1.55
     purpoſe
    1.53
    Activations Density 1.633%

    No Known Activations