© 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. 18-GEMMASCOPE-RES-16K
    11. 1627
    Prev
    Next
    INDEX
    Explanations

    legal terminology and specific references to judicial cases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Citations using "U.S." and court information

    np_acts-logits-general · gemini-2.0-flash

    US Supreme Court citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LookAnd
    -0.55
    protoimpl
    -0.54
    .*")]
    -0.51
    fromnode
    -0.51
    UrlResolution
    -0.47
    AntiForgeryToken
    -0.47
     بيها
    -0.45
    GTCX
    -0.44
    Referencie
    -0.44
    CPtr
    -0.44
    POSITIVE LOGITS
    terase
    0.59
    webElementGuid
    0.58
    featureID
    0.58
    internalType
    0.56
    bootstrapcdn
    0.56
    jsdelivr
    0.56
    withOpacity
    0.56
    ViewById
    0.56
    AuthProvider
    0.54
     viewType
    0.54
    Activations Density 0.773%

    No Known Activations