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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 33-GEMMASCOPE-RES-131K
    6. 65957
    Prev
    Next
    INDEX
    Explanations

    terms related to media management and file extraction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_131k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DIPSETTING
    -0.39
    Portail
    -0.34
    ToTable
    -0.33
     sostanza
    -0.32
    舺
    -0.31
     Vorteile
    -0.31
     sustancia
    -0.31
    EndProject
    -0.31
    IsSuccess
    -0.30
    setViewportView
    -0.30
    POSITIVE LOGITS
     metadata
    1.09
     thumbnails
    1.04
     thumbnail
    0.98
     Metadata
    0.97
     captions
    0.96
     caption
    0.95
     watermark
    0.94
     Thumbnails
    0.88
     Thumbnail
    0.84
     tagging
    0.83
    Activations Density 0.037%

    No Known Activations