© 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
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 8754
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a desire for knowledge or information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    migrationBuilder
    -0.78
    AnimationsModule
    -0.73
    Derbyniad
    -0.67
    évaluateur
    -0.60
    
    -0.58
    styleType
    -0.57
    izr
    -0.57
    UrlResolution
    -0.56
     loadImage
    -0.55
     ostavi
    -0.53
    POSITIVE LOGITS
     know
    2.88
    Know
    2.27
    know
    2.27
     Know
    2.22
     KNOW
    2.02
     knows
    1.99
    KNOW
    1.89
    knows
    1.77
     Knows
    1.57
     knew
    1.56
    Activations Density 0.148%

    No Known Activations