© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 12225
    Prev
    Next
    INDEX
    Explanations

    mentions of legal or official entities and their addresses

    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
     noDo
    -0.65
    WireFormatLite
    -0.60
     sorti
    -0.54
    GALLERY
    -0.53
     ✭✭
    -0.52
    (&:
    -0.51
    例文帳に追加
    -0.50
    DoubleQuotes
    -0.50
    зулта
    -0.49
     ExecuteAsync
    -0.48
    POSITIVE LOGITS
     Box
    1.19
    Box
    1.13
     box
    1.01
     PO
    1.01
     BOX
    0.96
    Attn
    0.90
    PO
    0.89
    box
    0.89
    boxes
    0.86
    BOX
    0.86
    Activations Density 0.150%

    No Known Activations