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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 3-GEMMASCOPE-RES-16K
    6. 10205
    Prev
    Next
    INDEX
    Explanations

    references to teams and teamwork contextually related to collaboration and management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sities
    -0.74
     GenerationType
    -0.69
    ]));
    
    -0.63
    ('.'
    -0.62
     Kraus
    -0.61
    canes
    -0.58
    wendig
    -0.58
    kinh
    -0.57
    nä
    -0.57
    ↴
    -0.56
    POSITIVE LOGITS
     team
    3.22
    Team
    3.07
     Team
    3.07
    team
    2.99
     TEAM
    2.85
     teams
    2.79
    TEAM
    2.70
     Teams
    2.56
    teams
    2.49
    Teams
    2.35
    Activations Density 0.030%

    No Known Activations