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. 11-GEMMASCOPE-RES-16K
    6. 5327
    Prev
    Next
    INDEX
    Explanations

    long sequences of underscores or whitespace characters

    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
    ambi
    -0.97
     Frei
    -0.97
    ioni
    -0.92
    MISS
    -0.91
     المعيارى
    -0.90
     Koro
    -0.89
    fraid
    -0.89
    bied
    -0.88
    brates
    -0.87
    脚注の使い方
    -0.87
    POSITIVE LOGITS
    Berna
    0.86
    er
    0.81
     Maguire
    0.80
     Hanne
    0.79
     Halen
    0.78
    ContextHolder
    0.77
     Hamlin
    0.76
     VIII
    0.76
    ậc
    0.74
    Contracts
    0.73
    Activations Density 0.101%

    No Known Activations