© 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. 39-GEMMASCOPE-RES-16K
    11. 3170
    Prev
    Next
    INDEX
    Explanations

    code-related discussions focusing on commands and their evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MergeFrom
    -0.51
    MLLoader
    -0.49
    ########.
    -0.47
    tonode
    -0.45
     resourceCulture
    -0.44
     AssemblyProduct
    -0.42
     незавершена
    -0.40
    makeConstraints
    -0.39
     Bolton
    -0.39
    ClientRect
    -0.39
    POSITIVE LOGITS
     quotes
    1.42
     quote
    1.39
     escape
    1.37
     quotation
    1.32
     quoted
    1.32
     escapes
    1.28
     escaped
    1.28
     quoting
    1.27
     escaping
    1.23
     Escape
    1.22
    Activations Density 0.766%

    No Known Activations