© 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. 3405
    Prev
    Next
    INDEX
    Explanations

    content related to evaluation and assessment processes

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

    phrases that express urgency or calls to action with temporal importance.

    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
    expandindo
    -0.53
    Hentet
    -0.39
    บัติ
    -0.39
     CreateTagHelper
    -0.39
     otomatig
    -0.38
     tremp
    -0.36
    wanzig
    -0.35
    ็จ
    -0.35
    inige
    -0.35
     terle
    -0.34
    POSITIVE LOGITS
     reconsider
    1.69
     review
    1.67
     reconsideration
    1.56
     reass
    1.54
     revis
    1.51
     rethink
    1.48
     revisit
    1.44
     ree
    1.44
    review
    1.41
    Review
    1.40
    Activations Density 0.350%

    No Known Activations