© 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. 20-GEMMASCOPE-RES-16K
    11. 3882
    Prev
    Next
    INDEX
    Explanations

    statements related to statistical or quantitative analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    phrases describing statistical or computational qualities like accuracy, complexity, and performance.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     houſe
    -0.52
     fons
    -0.51
     '\\;'
    -0.49
    ReusableCell
    -0.48
     Савезне
    -0.48
     cem
    -0.47
    delwed
    -0.47
     ſche
    -0.47
     alber
    -0.46
     uLocal
    -0.46
    POSITIVE LOGITS
    CppMethod
    0.54
    AccessorTable
    0.53
    AutoScaleMode
    0.48
     largely
    0.44
    matchCondition
    0.42
     very
    0.42
     varies
    0.42
     fronteras
    0.42
     архивлан
    0.40
     sorpresas
    0.40
    Activations Density 0.512%

    No Known Activations