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. 20-GEMMASCOPE-RES-16K
    6. 8066
    Prev
    Next
    INDEX
    Explanations

    references to organizations or groups, especially those associated with the word "club."

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

    a sports club

    np_acts-logits-general · gemini-2.0-flash

    club plus team names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    ]))
    
    -0.80
     consultato
    -0.80
    styleType
    -0.76
    rungsseite
    -0.76
    BeginInit
    -0.74
    LookAnd
    -0.70
    parsedMessage
    -0.70
    guenos
    -0.70
    Hochspringen
    -0.69
    ellees
    -0.69
    POSITIVE LOGITS
    bing
    0.81
     members
    0.78
     club
    0.78
     membership
    0.76
    bers
    0.75
     clubs
    0.74
    CLUB
    0.74
     Clubs
    0.74
     Club
    0.72
     clube
    0.72
    Activations Density 0.040%

    No Known Activations