© 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. 13485
    Prev
    Next
    INDEX
    Explanations

    the presence of negative phrases or words indicating denial or rejection

    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
    ArgsConstructor
    -0.49
    scriptId
    -0.48
    VersionUID
    -0.47
    EndInit
    -0.47
     jspb
    -0.46
     localisation
    -0.45
    
    -0.45
    others
    -0.45
     kapturem
    -0.45
    ResumeLayout
    -0.43
    POSITIVE LOGITS
     not
    0.99
     tidak
    0.76
     never
    0.74
     doesnt
    0.71
     didnt
    0.71
    t
    0.70
    Tidak
    0.70
     NOT
    0.66
     ไม่
    0.66
    not
    0.65
    Activations Density 0.157%

    No Known Activations