© 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-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 8895
    Prev
    Next
    INDEX
    Explanations

    requests for information and support in problem-solving contexts

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

    expressions of inability or failure to locate something.

    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
    PerformLayout
    -0.44
    AnimationsModule
    -0.40
    Hochspringen
    -0.40
     betweenstory
    -0.40
    出版年
    -0.39
    AxisAlignment
    -0.39
    ↹
    -0.36
     ويكيپيديا
    -0.36
    ंदीखरीदारी
    -0.36
    EnableWeb
    -0.35
    POSITIVE LOGITS
     found
    2.52
     find
    2.39
     finding
    2.36
    found
    2.23
     finds
    2.22
    find
    2.19
     Found
    2.17
     FIND
    2.16
    找到
    2.13
     Find
    2.09
    Activations Density 0.846%

    No Known Activations