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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 21-GEMMASCOPE-RES-16K
    6. 13885
    Prev
    Next
    INDEX
    Explanations

    tokens related to programming and code structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    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
    -0.70
    :+:
    -0.67
    GraphicsUnit
    -0.64
    i
    -0.63
    a
    -0.63
    ClientSize
    -0.56
     گوید
    -0.55
    й
    -0.53
    IBOutlet
    -0.53
    s
    -0.53
    POSITIVE LOGITS
    NUMX
    0.76
    ftagPool
    0.69
     cref
    0.68
    VersionUID
    0.68
     Chriſt
    0.68
     Chrift
    0.66
     Theſe
    0.66
     Jefus
    0.65
     Roskov
    0.64
    djangoproject
    0.64
    Activations Density 0.180%

    No Known Activations