© 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-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 15647
    Prev
    Next
    INDEX
    Explanations

    references to numerical data and statistics within a structured context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
     teg
    -0.48
     SPC
    -0.46
     tante
    -0.44
     surla
    -0.43
    inSlope
    -0.43
    riwal
    -0.43
    
    -0.41
     Speak
    -0.40
    SequentialGroup
    -0.40
    findpost
    -0.40
    POSITIVE LOGITS
    новништво
    0.55
     connexe
    0.51
     ProtoMessage
    0.47
    Sklici
    0.47
    intenant
    0.47
     conmigo
    0.46
    fhir
    0.43
     exportaciones
    0.42
     estatua
    0.42
    MigrationBuilder
    0.41
    Activations Density 0.127%

    No Known Activations