© 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. 33-GEMMASCOPE-RES-16K
    6. 7746
    Prev
    Next
    INDEX
    Explanations

    elements of error handling in code

    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
     Amongst
    -0.68
     Whilst
    -0.65
     perchè
    -0.65
     amongst
    -0.59
    Whilst
    -0.56
     focussed
    -0.56
     skall
    -0.55
     = 
    -0.54
     diantaranya
    -0.53
     diatas
    -0.52
    POSITIVE LOGITS
    MessageOf
    0.63
    SharedCtor
    0.54
    akaian
    0.53
    Vidite
    0.47
    thâu
    0.44
    تفصیلات
    0.44
    astify
    0.44
     Chwiliwch
    0.43
    GTCX
    0.43
    хьтан
    0.43
    Activations Density 0.084%

    No Known Activations