© 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. 33-GEMMASCOPE-RES-16K
    11. 139
    Prev
    Next
    INDEX
    Explanations

    details about various types of buckles and their specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __((
    -0.32
     chopped
    -0.32
    ensement
    -0.31
     pied
    -0.29
     treadmill
    -0.28
    getJSONArray
    -0.27
     apron
    -0.27
     telev
    -0.27
     prognostic
    -0.27
     гене
    -0.27
    POSITIVE LOGITS
     clip
    1.02
     clips
    0.97
     hook
    0.93
     hooks
    0.91
     buckle
    0.91
     clasp
    0.90
     Clips
    0.90
     fastener
    0.89
     snap
    0.86
     Clip
    0.85
    Activations Density 0.332%

    No Known Activations