© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 461
    Prev
    Next
    INDEX
    Explanations

    indicators of programming syntax and commands

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

    the presence of the token "<bos>", indicating the beginning of a sequence

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

    question prompt, code, or specific value assignment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    存于互联网档案馆
    -0.68
    CppMethod
    -0.65
    MockMvc
    -0.63
     تكبرها
    -0.61
    IVEREF
    -0.58
     EClass
    -0.56
     ***!
    -0.56
     الرياضيه
    -0.52
    ValueGeneration
    -0.52
     estatales
    -0.51
    POSITIVE LOGITS
    </h3>
    0.82
    <b>
    0.64
    toContain
    0.64
    XmlAccessType
    0.61
    ArgsConstructor
    0.60
    :\\
    0.59
    exels
    0.59
    ;'>
    0.57
    \\
    0.56
    !(:
    0.55
    Activations Density 0.337%

    No Known Activations