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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 80761
    Prev
    Next
    INDEX
    Explanations

    key terms related to community, branding, and essential qualities in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     propOrder
    -0.88
    +#+#
    -0.66
    tagHelperRunner
    -0.61
    setVerticalGroup
    -0.57
    AndEndTag
    -0.57
     initComponents
    -0.56
    ########.
    -0.55
    IntoConstraints
    -0.55
     wikipagina
    -0.54
     հղումներ
    -0.54
    POSITIVE LOGITS
    Hentet
    0.42
    SpringRunner
    0.39
    mapStateToProps
    0.35
     californ
    0.34
    COUVER
    0.33
    Nih
    0.32
    Parcelize
    0.32
     honn
    0.32
    igshid
    0.32
     erat
    0.31
    Activations Density 0.039%

    No Known Activations