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. 8535
    Prev
    Next
    INDEX
    Explanations

    references to academic publications and their specific formats

    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
    ftagPool
    -0.73
    Pyx
    -0.54
    brigens
    -0.53
     残
    -0.53
    IntoConstraints
    -0.53
    chyma
    -0.52
     插图
    -0.51
    raits
    -0.50
    Чита
    -0.50
     Physically
    -0.50
    POSITIVE LOGITS
    PhysRev
    0.83
    amping
    0.68
    SuspendLayout
    0.57
     REV
    0.57
     Rev
    0.54
    olutions
    0.53
    REV
    0.52
     rev
    0.52
    rev
    0.51
    ResumeLayout
    0.51
    Activations Density 0.092%

    No Known Activations