© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 15281
    Prev
    Next
    INDEX
    Explanations

    phrases indicating organization and procedural steps

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_25/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.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    いかがでしょうか
    -0.43
     abstrait
    -0.41
    いかが
    -0.37
    sizePolicy
    -0.35
     Evangelio
    -0.34
     confianza
    -0.34
     those
    -0.33
     zakresie
    -0.33
     parcela
    -0.32
    立ち
    -0.31
    POSITIVE LOGITS
     below
    0.98
    below
    0.86
     Below
    0.82
    Below
    0.81
     nedan
    0.77
    rungsseite
    0.76
     next
    0.74
    下面
    0.73
     hieronder
    0.73
     hereinafter
    0.70
    Activations Density 0.524%

    No Known Activations