© 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. 801
    Prev
    Next
    INDEX
    Explanations

    references to a specific program or initiative involving challenges

    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
    *
    -0.27
    r
    -0.27
    s
    -0.25
     
    -0.25
     s
    -0.25
    ="
    -0.25
    ↵
    -0.24
     le
    -0.24
     verbringen
    -0.24
    ↵↵
    -0.24
    POSITIVE LOGITS
     queſta
    0.90
    batore
    0.89
     ModelExpression
    0.86
     Challenge
    0.80
     defaultstate
    0.78
     $_(
    0.77
     Chall
    0.76
    tagHelperRunner
    0.76
    ੝
    0.76
    ALLENGE
    0.75
    Activations Density 0.074%

    No Known Activations