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. 3-GEMMASCOPE-RES-16K
    6. 12886
    Prev
    Next
    INDEX
    Explanations

    references to environmental themes and planetary concepts

    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
     تضيفلها
    -0.85
     estimés
    -0.79
    ]))
    
    -0.63
     gynhyrchwyd
    -0.63
    IntoConstraints
    -0.63
    ]^{-
    -0.62
    rrggbb
    -0.61
     kasarigan
    -0.60
    клопе
    -0.60
     GetEnumerator
    -0.60
    POSITIVE LOGITS
     trouxe
    0.42
    eabouts
    0.40
    KommentareTeilen
    0.39
     setType
    0.39
    δη
    0.39
     responsáveis
    0.39
    CodeAnalysis
    0.39
     Jadi
    0.38
     getModel
    0.38
     useHistory
    0.38
    Activations Density 1.232%

    No Known Activations