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. 5-GEMMASCOPE-RES-16K
    6. 5469
    Prev
    Next
    INDEX
    Explanations

    structured data with various key-value pairs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :✨
    -1.24
     Administrativna
    -1.20
     Roskov
    -1.09
     Италијани
    -1.08
     itſelf
    -1.07
     ſche
    -1.03
    aarrggbb
    -1.02
     autorytatywna
    -1.00
     Majefty
    -0.99
     Reſ
    -0.98
    POSITIVE LOGITS
    </strong>
    0.53
    </em>
    0.52
     $\
    0.50
    .
    0.49
    </u>
    0.45
    </h2>
    0.45
    ↵
    0.44
     con
    0.43
     G
    0.43
     O
    0.42
    Activations Density 0.863%

    No Known Activations