Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 2068
    Prev
    Next
    INDEX
    Explanations

    references to parameters and their handling in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tartalomajánló
    -0.95
    Datuak
    -0.88
    circledR
    -0.85
    CodeAnalysis
    -0.83
    LookAnd
    -0.82
    rsiniz
    -0.80
     SafeMath
    -0.79
     Esmeralda
    -0.79
    IContainer
    -0.78
    CodeAttribute
    -0.78
    POSITIVE LOGITS
     params
    1.77
    params
    1.76
    Params
    1.43
     Params
    1.37
    getParams
    1.30
     useParams
    1.10
    PARAMS
    1.10
    Param
    0.92
     Wals
    0.91
     bParam
    0.91
    Activations Density 0.051%

    No Known Activations