© 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. 2-GEMMASCOPE-RES-16K
    6. 4045
    Prev
    Next
    INDEX
    Explanations

    terms that indicate influence and its effects

    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
    tagHelperRunner
    -0.57
    grab
    -0.46
     vectorielles
    -0.46
     rubbing
    -0.45
     grab
    -0.44
     Irrit
    -0.43
    string
    -0.43
     Réponses
    -0.43
     drill
    -0.43
     crippling
    -0.42
    POSITIVE LOGITS
    Influ
    0.63
     EconPapers
    0.61
     influenced
    0.55
     Influ
    0.54
     Influences
    0.53
    Influence
    0.53
     influences
    0.52
     roof
    0.50
     Influence
    0.49
     INFLU
    0.49
    Activations Density 0.064%

    No Known Activations