Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 124917
    Prev
    Next
    INDEX
    Explanations

    phrases related to fashion and wedding dresses

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

    clothing styles and events

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    aarrggbb
    -0.71
    SequentialGroup
    -0.69
     للمعارف
    -0.67
     AppCompatTheme
    -0.66
    BeginContext
    -0.63
    :✨
    -0.61
     autorytatywna
    -0.59
     صوتيه
    -0.59
     onPostExecute
    -0.58
    ponses
    -0.57
    POSITIVE LOGITS
    Position
    0.31
     integrated
    0.30
    bi
    0.29
    </blockquote>
    0.29
     facility
    0.28
     position
    0.28
     pull
    0.28
    وئ
    0.28
    ătoare
    0.28
     power
    0.28
    Activations Density 0.022%

    No Known Activations