© 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. 10-GEMMASCOPE-RES-16K
    6. 1994
    Prev
    Next
    INDEX
    Explanations

    complex mathematical or programming structures and syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     surla
    -1.14
    Rüyada
    -0.99
     estekak
    -0.97
    SourceChecksum
    -0.96
    ьаж
    -0.89
    InitVars
    -0.88
     '\\;'
    -0.85
     Италијани
    -0.78
    Cyfeiriadau
    -0.78
     &___
    -0.75
    POSITIVE LOGITS
    存于互联网档案馆
    0.54
     rowspan
    0.54
     nữa
    0.51
    amaño
    0.50
    NOPQRST
    0.49
     îns
    0.49
     thậm
    0.48
    mathrm
    0.44
    </thead>
    0.44
     اغ
    0.43
    Activations Density 0.323%

    No Known Activations