© 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. 31-GEMMASCOPE-RES-16K
    11. 8906
    Prev
    Next
    INDEX
    Explanations

    HTML elements related to job postings and details

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

    HTML and JSX closing tags.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EnableWeb
    -0.52
    principalColumn
    -0.50
    发表于
    -0.49
    omock
    -0.49
     мәкал
    -0.46
    IContainer
    -0.44
     ProtoMessage
    -0.44
    tranno
    -0.43
    RemoveField
    -0.43
    xiety
    -0.42
    POSITIVE LOGITS
    <h4>
    1.46
    <h2>
    1.46
    <h3>
    1.44
    <h5>
    1.34
    <h6>
    1.18
    <h1>
    1.16
    <table>
    0.85
    <caption>
    0.53
    <th>
    0.51
    <tr>
    0.51
    Activations Density 0.443%

    No Known Activations