© 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. 5-GEMMASCOPE-RES-16K
    6. 7793
    Prev
    Next
    INDEX
    Explanations

    specific mentions of "details" or "detail."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     otomatig
    -0.76
     Cowper
    -0.75
    Mover
    -0.73
    ագրություններ
    -0.72
    cabulary
    -0.70
     الدولي
    -0.70
    GridColumn
    -0.69
    ρίς
    -0.67
     Buchanan
    -0.67
     cups
    -0.67
    POSITIVE LOGITS
     details
    2.50
     detail
    2.22
     Details
    2.18
    details
    2.06
    Details
    2.04
     Detail
    2.02
     DETAILS
    1.97
    detail
    1.88
    Detail
    1.81
     détails
    1.75
    Activations Density 0.050%

    No Known Activations