© 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-2-2B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 6043
    Prev
    Next
    INDEX
    Explanations

    elements that represent variable names and assignments in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    تقاوى
    -0.54
    uesia
    -0.52
    Portail
    -0.49
     FetchType
    -0.49
    Lead
    -0.48
     Italijanski
    -0.45
     urbanos
    -0.44
     ролях
    -0.44
     Lead
    -0.44
    vábbi
    -0.43
    POSITIVE LOGITS
     AssemblyTitle
    0.97
     ModelExpression
    0.74
    istoitu
    0.70
     resourceCulture
    0.70
    UnsafeEnabled
    0.62
     AssemblyProduct
    0.62
     }{@
    0.60
    makeConstraints
    0.60
     AssemblyCompany
    0.59
    Personendaten
    0.57
    Activations Density 0.044%

    No Known Activations