© 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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 7030
    Prev
    Next
    INDEX
    Explanations

    phrases indicating minimal or near occurrences of events or conditions

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

    "almost" or "close to"

    np_acts-logits-general · gemini-2.0-flash

    barely or hardly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nějak
    -0.33
     definitely
    -0.31
     Ternyata
    -0.31
     Khusus
    -0.30
    weder
    -0.30
     wcześniej
    -0.30
     вдруг
    -0.29
     gezet
    -0.29
     irgendwie
    -0.29
     gantung
    -0.29
    POSITIVE LOGITS
    awtextra
    0.86
     barely
    0.86
    Almost
    0.80
     quase
    0.77
    almost
    0.76
     Almost
    0.73
     scarcely
    0.73
     Hardly
    0.71
     almost
    0.71
    幾乎
    0.69
    Activations Density 0.409%

    No Known Activations