© 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. 13485
    Prev
    Next
    INDEX
    Explanations

    terms related to direct interaction and integration within scientific contexts

    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
    est
    -0.53
    če
    -0.49
    na
    -0.46
    A
    -0.46
    va
    -0.46
    gn
    -0.45
    is
    -0.43
    for
    -0.43
    ftp
    -0.43
    ul
    -0.43
    POSITIVE LOGITS
    directly
    0.88
     Directly
    0.83
     itſelf
    0.81
     selve
    0.80
     directement
    0.77
    AnimationsModule
    0.76
     direta
    0.76
     directly
    0.76
    当场
    0.75
     مستقیم
    0.75
    Activations Density 0.545%

    No Known Activations