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 - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 703
    Prev
    Next
    INDEX
    Explanations

    technical jargon related to image formats and URLs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     intenta
    -0.35
     Hermans
    -0.31
     creemos
    -0.31
     apunta
    -0.25
    ↵
    -0.25
     Staats
    -0.25
    räume
    -0.25
    TimeStamp
    -0.25
     accused
    -0.24
     immediately
    -0.24
    POSITIVE LOGITS
     BoxFit
    0.88
    StoryboardSegue
    0.88
    elemField
    0.84
    setVerticalGroup
    0.83
    IntoConstraints
    0.81
    DockStyle
    0.80
    twimg
    0.77
     للاسماء
    0.76
    styleType
    0.75
    TagMode
    0.75
    Activations Density 0.129%

    No Known Activations