© 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-2-2B
    7. Residual Stream - 16k
    9. 7-GEMMASCOPE-RES-16K
    11. 4709
    Prev
    Next
    INDEX
    Explanations

    declarations related to private and readonly variables in coding contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ழ
    -0.55
     ""],
    -0.55
    mazan
    -0.50
     afecta
    -0.50
    elemField
    -0.47
     médicale
    -0.47
    StructEnd
    -0.47
    Ỗ
    -0.47
    Caracter
    -0.47
    Odkazy
    -0.47
    POSITIVE LOGITS
    Portale
    0.88
    WireFormatLite
    0.75
    sizeCache
    0.75
    synthesize
    0.67
    subpackage
    0.65
    DllImport
    0.61
     Meksiku
    0.60
     pylint
    0.60
    abstractmethod
    0.58
     readonly
    0.56
    Activations Density 0.020%

    No Known Activations