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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 3295
    Prev
    Next
    INDEX
    Explanations

    details related to automotive parts and their identification

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

    following "part(s)" or "Part"

    np_acts-logits-general · gemini-2.0-flash

    parts and spares

    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
     initComponents
    -0.49
     utafitiHapana
    -0.49
    
    -0.47
     Réponses
    -0.44
    httphttps
    -0.41
    opsis
    -0.41
    casian
    -0.41
    efel
    -0.40
     समीक्षक
    -0.40
     estés
    -0.40
    POSITIVE LOGITS
     Parts
    0.68
    Parts
    0.66
     spares
    0.58
     parts
    0.57
    Spare
    0.55
     Spare
    0.54
     PARTS
    0.53
    parts
    0.53
    spare
    0.51
     spare
    0.50
    Activations Density 0.171%

    No Known Activations