© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 11095
    Prev
    Next
    INDEX
    Explanations

    questions related to clarifying user intent or seeking information

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

    Question beginnings in French/Spanish/other languages

    np_acts-logits-general · gemini-2.0-flash

    Questions about software

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Normdatei
    -0.58
    complexContent
    -0.58
    лтемелер
    -0.52
    openzeppelin
    -0.52
    AddTagHelper
    -0.51
     ModelExpression
    -0.50
    GTCX
    -0.49
    ruptedException
    -0.49
    optionalTypeArgs
    -0.49
     HasFactory
    -0.49
    POSITIVE LOGITS
    permalink
    0.32
     상세
    0.31
     Савезне
    0.31
     solches
    0.30
    ('/:
    0.30
    !("{
    0.29
    เฉ
    0.29
    ("/:
    0.28
    lusconi
    0.28
    ombic
    0.28
    Activations Density 0.416%

    No Known Activations