© 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-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 2625
    Prev
    Next
    INDEX
    Explanations

    attributes or values assigned in a markup or structured data format

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

    XML and HTML tag attributes and parameter names.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    attribute–value assignments in markup (HTML/XML) tags, i.e., equals-with-quoted values within tag attributes.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    XML/HTML attribute assignment syntax (e.g., `name="`, `value=`)

    oai_token-act-pair · deepseek-r1Triggered by @jyhe0408

    the equals sign followed by a quotation mark in XML/HTML attribute assignments.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    instancetype
    -0.53
    XH
    -0.50
    onStop
    -0.47
    SourceChecksum
    -0.45
    DataSetChanged
    -0.44
     Util
    -0.44
    ）.
    -0.44
    ますね
    -0.43
     SOS
    -0.43
     Hund
    -0.42
    POSITIVE LOGITS
    ="
    0.96
    ='
    0.69
    ]="
    0.61
    )="
    0.59
     $=
    0.59
    PathVariable
    0.57
     ویکی‌پدیای
    0.57
    ="_
    0.56
     autorytatywna
    0.56
    ={
    0.55
    Activations Density 0.132%

    No Known Activations