© 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. 37-GEMMASCOPE-RES-16K
    11. 939
    Prev
    Next
    INDEX
    Explanations

    technical issues related to software updates and errors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     toekomst
    -0.54
     szükség
    -0.53
     rahasia
    -0.49
    chauung
    -0.46
     przeznac
    -0.46
     znajdziesz
    -0.45
     hiszen
    -0.44
     Öffentlichkeit
    -0.44
    だからこそ
    -0.43
     Menschheit
    -0.43
    POSITIVE LOGITS
     consistently
    0.81
     intermittently
    0.73
     everytime
    0.69
     seems
    0.68
     seem
    0.66
     Seems
    0.65
     seemed
    0.65
     randomly
    0.63
     noticed
    0.63
     Tried
    0.61
    Activations Density 0.762%

    No Known Activations