© 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. 2951
    Prev
    Next
    INDEX
    Explanations

    references to health organizations and regulatory agencies

    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
    await
    -0.52
    şam
    -0.49
    同步
    -0.48
    ched
    -0.45
    日起
    -0.45
    én
    -0.44
    doras
    -0.44
    uniq
    -0.44
    deepcopy
    -0.44
    الإنجليزية
    -0.44
    POSITIVE LOGITS
    Демографія
    0.86
    цездатний
    0.84
     utafitiHapana
    0.81
    MigrationBuilder
    0.80
     ujednoznacz
    0.80
     <=",
    0.79
     ModelExpression
    0.79
    ItemBackground
    0.78
    曖昧さ回避
    0.78
     الحره
    0.76
    Activations Density 1.856%

    No Known Activations