© 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. 3583
    Prev
    Next
    INDEX
    Explanations

    descriptions of strong female characters and their attributes

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

    discussions of diversity, representation, and inclusion of women and marginalized groups in media and society.

    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
     pertanto
    -0.55
    Btw
    -0.55
     Hence
    -0.50
    NoOf
    -0.49
     oppure
    -0.49
    FYI
    -0.47
     ppl
    -0.47
     Deshalb
    -0.45
     Toutefois
    -0.45
     nyky
    -0.45
    POSITIVE LOGITS
    PullParser
    0.61
    ReusableCell
    0.59
    createForm
    0.58
     crossorigin
    0.57
     FixedUpdate
    0.56
    fromCharCode
    0.56
     esche
    0.56
     newVal
    0.55
    asdf
    0.55
    ConverterFactory
    0.55
    Activations Density 2.114%

    No Known Activations