© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 6686
    Prev
    Next
    INDEX
    Explanations

    instances of special tokens or markers indicating the beginning or end of a segment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SourceChecksum
    -1.06
    Personendaten
    -0.99
     nakalista
    -0.89
     AssemblyCulture
    -0.88
    Autoritní
    -0.86
    IsMutable
    -0.86
    yntaxException
    -0.85
     Савезне
    -0.83
    aarrggbb
    -0.83
     defaultstate
    -0.80
    POSITIVE LOGITS
    ↵↵
    0.55
    <eos>
    0.49
    ↵↵↵
    0.48
     affatto
    0.48
    ’
    0.46
    0.45
    ور
    0.43
    <blockquote>
    0.42
     jeb
    0.42
    ‍
    0.42
    Activations Density 0.160%
    No Known Activations