© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 15253
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "community" and related terms

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

    "community"

    np_acts-logits-general · gemini-2.0-flash

    community and its contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     Irán
    -0.62
     Japón
    -0.50
    <bos>
    -0.47
     Moscú
    -0.45
     París
    -0.45
     Turquía
    -0.45
     Egipto
    -0.44
     last
    -0.41
     Suiza
    -0.40
     eletrônico
    -0.40
    POSITIVE LOGITS
     community
    1.27
    Community
    1.24
     Community
    1.20
    community
    1.17
     communities
    1.14
     COMMUNITY
    1.14
    COMMUNITY
    1.12
     Communities
    1.08
    Communities
    1.07
    communities
    1.01
    Activations Density 0.036%

    No Known Activations