© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 34-GEMMASCOPE-RES-16K
    6. 7776
    Prev
    Next
    INDEX
    Explanations

    themes related to grassroots organizing and community empowerment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     oprot
    -0.49
    Golf
    -0.44
    addHandler
    -0.40
     Golf
    -0.39
     golf
    -0.38
     GOLF
    -0.37
    ゴルフ
    -0.36
     modernisation
    -0.36
    woordig
    -0.35
    Leistungs
    -0.35
    POSITIVE LOGITS
     cooperative
    0.80
     community
    0.77
     Community
    0.75
     cooperatives
    0.73
     COMMUNITY
    0.73
     participatory
    0.71
    community
    0.70
     anarchist
    0.70
    Community
    0.69
     cooper
    0.67
    Activations Density 0.423%

    No Known Activations