© 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. 3-GEMMASCOPE-RES-16K
    6. 11861
    Prev
    Next
    INDEX
    Explanations

    mathematical notations and symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parsedMessage
    -0.49
    PageState
    -0.43
    تقاوى
    -0.43
    ьаж
    -0.43
     chủ
    -0.42
    CppCodeGen
    -0.41
    ListData
    -0.41
    thâu
    -0.41
     Kers
    -0.41
    elemField
    -0.41
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.82
    $$\
    0.72
    TagMode
    0.70
     متعلقه
    0.69
    CGRectMake
    0.69
    */;
    0.68
    esez
    0.67
    CppMethod
    0.66
    styleType
    0.64
    onOptions
    0.64
    Activations Density 0.433%

    No Known Activations