© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 9629
    Prev
    Next
    INDEX
    Explanations

    sequences of whitespace or tab characters

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

    sections of source code or programming-style text (code snippets with syntax, method calls, and indentation)

    oai_token-act-pair · gpt-5Triggered by @liuliujiujiu05
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AccessorTable
    -0.76
    setViewName
    -0.64
    WriteBarrier
    -0.63
    Données
    -0.60
    données
    -0.60
    #
    -0.58
     industriel
    -0.58
     Answered
    -0.56
     onPostExecute
    -0.56
     "")
    
    -0.56
    POSITIVE LOGITS
    homonymie
    0.72
     Catalana
    0.60
    principalColumn
    0.47
    RenderAtEndOf
    0.44
    MMdd
    0.44
    fluent
    0.43
     IVA
    0.43
    ături
    0.42
    ́
    0.42
     magasiner
    0.41
    Activations Density 0.136%

    No Known Activations