© 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. 1458
    Prev
    Next
    INDEX
    Explanations

    key metrics or classifications of items across different categories

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

    Followed by "each"

    np_acts-logits-general · gemini-2.0-flash

    each / every

    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
    ########.
    -0.48
    裟
    -0.47
    TextSpan
    -0.42
    IntoConstraints
    -0.41
    richTextPanel
    -0.40
    leby
    -0.40
    bitat
    -0.39
     avis
    -0.39
    gernaut
    -0.36
    hesda
    -0.36
    POSITIVE LOGITS
     each
    1.04
     every
    1.00
     każdej
    0.84
     fiecare
    0.83
     varje
    0.83
     każdego
    0.81
     setiap
    0.80
     каждую
    0.79
     chaque
    0.79
     każdym
    0.78
    Activations Density 0.715%

    No Known Activations