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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 10359
    Prev
    Next
    INDEX
    Explanations

    mentions of volunteerism and related activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    日閲覧
    -0.84
    featureID
    -0.57
    hintText
    -0.53
    ]_{\
    -0.52
    ereum
    -0.50
    تيجة
    -0.50
     web
    -0.50
     đu
    -0.49
    InternalFrame
    -0.49
    EndTag
    -0.49
    POSITIVE LOGITS
     volunteer
    3.26
     volunteers
    3.01
    Volunteer
    2.83
     Volunteer
    2.77
    volunteer
    2.74
     volunteered
    2.69
     volunteering
    2.65
     Volunteers
    2.51
    Volunteers
    2.49
     volunte
    1.95
    Activations Density 0.063%

    No Known Activations