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. 15-GEMMASCOPE-RES-16K
    6. 12933
    Prev
    Next
    INDEX
    Explanations

    terms related to social and environmental concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    resave
    -0.79
     indépendante
    -0.75
    hasPermission
    -0.74
     suprême
    -0.73
     Spielberg
    -0.72
    zzleHttp
    -0.71
     ketones
    -0.70
    razine
    -0.69
    ]")]
    -0.67
     kDa
    -0.67
    POSITIVE LOGITS
    SOCIAL
    1.18
     social
    1.14
     Social
    1.12
     SOCIAL
    1.11
    Social
    1.11
     socials
    1.08
    social
    1.00
     Soci
    0.93
     socially
    0.88
    Soci
    0.87
    Activations Density 0.038%

    No Known Activations