© 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. 20-GEMMASCOPE-RES-16K
    6. 14614
    Prev
    Next
    INDEX
    Explanations

    terms related to financial metrics and statistical analyses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     disambiguazione
    -0.62
    expandindo
    -0.59
    IsMutable
    -0.58
    úgó
    -0.57
    principalColumn
    -0.57
     snippetHide
    -0.57
     Italij
    -0.57
     autorytatywna
    -0.56
    rungsseite
    -0.56
    ValueStyle
    -0.56
    POSITIVE LOGITS
     estimate
    0.45
     estimates
    0.39
     Net
    0.39
     Assim
    0.39
     estimated
    0.39
     factored
    0.38
     Wes
    0.38
     Ment
    0.37
    Net
    0.37
     Max
    0.37
    Activations Density 0.701%

    No Known Activations