© 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. 21-GEMMASCOPE-RES-16K
    11. 12196
    Prev
    Next
    INDEX
    Explanations

    specific names or terms related to biological or chemical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     harian
    -0.62
    en
    -0.59
     ​​
    -0.57
    도
    -0.56
     répondre
    -0.56
     mind
    -0.55
    位
    -0.53
    ︎
    -0.50
    ❷
    -0.50
    望
    -0.49
    POSITIVE LOGITS
    MethodManager
    0.91
    usermodel
    0.85
    tvguidetime
    0.82
     незавершена
    0.82
     CMM
    0.77
    CrossRef
    0.74
     Majefty
    0.73
    ttt
    0.72
    UnusedPrivate
    0.72
    LLocation
    0.72
    Activations Density 0.418%

    No Known Activations