© 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. 958
    Prev
    Next
    INDEX
    Explanations

    legal terminology and references related to law cases

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

    preceding a sentence or clause

    np_acts-logits-general · gemini-2.0-flash

    height in meters squared

    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
    تقاوى
    -0.94
     فريبيس
    -0.73
    ISupport
    -0.73
    GraphicsUnit
    -0.73
    twimg
    -0.72
    verwijspagina
    -0.70
    Bioaccumulative
    -0.69
     متعلقه
    -0.69
    MigrationBuilder
    -0.68
    Portail
    -0.67
    POSITIVE LOGITS
    oa̍t
    0.59
    .
    0.55
    oceros
    0.52
    ,
    0.51
    мум
    0.48
     betere
    0.47
     the
    0.47
    ?
    0.47
    とし
    0.46
     is
    0.46
    Activations Density 1.071%

    No Known Activations