© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 9895
    Prev
    Next
    INDEX
    Explanations

    structured programming concepts and methodologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CGContext
    -0.58
     autorytatywna
    -0.58
    rawDesc
    -0.54
     secundarios
    -0.54
    enuto
    -0.53
     Gato
    -0.52
    ODB
    -0.52
    cambrian
    -0.52
    ღ
    -0.52
    randomUUID
    -0.51
    POSITIVE LOGITS
     first
    0.91
    first
    0.91
     FIRST
    0.83
     Erster
    0.81
    First
    0.80
    unächst
    0.80
     First
    0.78
     first
    0.77
    แรก
    0.77
     första
    0.77
    Activations Density 0.623%

    No Known Activations