© 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. 8-GEMMASCOPE-RES-16K
    11. 6427
    Prev
    Next
    INDEX
    Explanations

    requests for assistance or support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_8/width_16k/average_l0_99
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     prominently
    -0.33
     series
    -0.32
     go
    -0.31
     kohta
    -0.31
     rather
    -0.30
     
    -0.30
    go
    -0.28
     not
    -0.28
     interface
    -0.28
     Scherer
    -0.28
    POSITIVE LOGITS
     help
    1.68
    help
    1.68
     Help
    1.65
    Help
    1.61
    HELP
    1.48
     assistance
    1.45
     HELP
    1.43
    assistance
    1.41
     Assistance
    1.38
     ayuda
    1.36
    Activations Density 0.156%

    No Known Activations