© 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. 12-GEMMASCOPE-RES-16K
    11. 3240
    Prev
    Next
    INDEX
    Explanations

    comparative phrases indicating slight changes or differences in measurements or qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bautizo
    -0.50
    vų
    -0.46
    のですか
    -0.44
     cementerio
    -0.42
     gouver
    -0.40
     absolutely
    -0.40
    quiera
    -0.40
     négoci
    -0.40
     publiques
    -0.39
     condenado
    -0.39
    POSITIVE LOGITS
    slightly
    0.75
     slightly
    0.69
     Slightly
    0.67
    Slightly
    0.65
     فريبيس
    0.63
     sedikit
    0.63
     nieco
    0.62
    somewhat
    0.62
     Somewhat
    0.61
     slight
    0.60
    Activations Density 0.904%

    No Known Activations