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. 9-GEMMASCOPE-RES-16K
    6. 15508
    Prev
    Next
    INDEX
    Explanations

    end punctuation and formatting tags, indicating closure or completion of sections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kishi
    -0.72
    хьтан
    -0.68
    Chham
    -0.64
    Controllo
    -0.63
     continúas
    -0.61
    ilent
    -0.58
    ệm
    -0.57
    IContainer
    -0.57
    chyma
    -0.56
     matchs
    -0.55
    POSITIVE LOGITS
    ↵↵
    1.06
    </blockquote>
    0.87
    ↵↵↵↵↵
    0.80
    ↵↵↵
    0.79
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.79
    </h3>
    0.77
    <eos>
    0.75
    :])
    0.73
    ↵↵↵↵↵↵
    0.72
    </h2>
    0.71
    Activations Density 0.079%

    No Known Activations