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-2-9B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 5570
    Prev
    Next
    INDEX
    Explanations

    references to groups and communities involved in activities or events

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

    preceding "club," "group," or similar terms

    np_acts-logits-general · gemini-2.0-flash

    clubs and groups

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enciaga
    -0.41
    稍
    -0.40
     narrowed
    -0.36
     dég
    -0.36
     eletrônico
    -0.35
     zatr
    -0.35
     designed
    -0.34
     setzte
    -0.33
     elef
    -0.33
    ServiceException
    -0.33
    POSITIVE LOGITS
     meetup
    0.86
     Meetup
    0.86
     hobby
    0.80
     club
    0.79
    hobby
    0.71
     clubs
    0.70
     CLUB
    0.69
     volunteer
    0.69
     klub
    0.69
     amateur
    0.68
    Activations Density 0.329%

    No Known Activations