© 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. 426
    Prev
    Next
    INDEX
    Explanations

    financial metrics and trends within economic reports

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

    numerical comparisons and percentage changes showing growth or decline.

    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
     AssemblyCulture
    -0.76
    帖最后由
    -0.71
    الحياه
    -0.63
    Kjelder
    -0.63
    ChildScrollView
    -0.62
     ब्रेकडाउन
    -0.62
    verifyException
    -0.61
     snippetHide
    -0.60
    ]")]
    -0.59
    EndContext
    -0.58
    POSITIVE LOGITS
     nearly
    0.36
    百分之
    0.34
    폭
    0.33
     twofold
    0.31
     substantial
    0.31
     sharp
    0.30
     threefold
    0.29
     dramatically
    0.28
     dramatic
    0.28
     almost
    0.27
    Activations Density 0.182%

    No Known Activations