© 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. 24-GEMMASCOPE-RES-16K
    11. 5846
    Prev
    Next
    INDEX
    Explanations

    technical terms and processes related to machine operation and assembly

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

    following a period

    np_acts-logits-general · gemini-2.0-flash

    whether or not

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    currently
    -0.79
     obecnie
    -0.75
     currently
    -0.74
     actuellement
    -0.72
     Currently
    -0.71
    Currently
    -0.70
     attualmente
    -0.67
     atualmente
    -0.66
     derzeit
    -0.63
     сейчас
    -0.60
    POSITIVE LOGITS
     was
    1.16
     had
    0.83
     knew
    0.81
     seemed
    0.80
     consisted
    0.80
     lacked
    0.79
     wasn
    0.79
     depended
    0.77
     vardı
    0.75
     gave
    0.73
    Activations Density 4.125%

    No Known Activations