© 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. 22-GEMMASCOPE-RES-16K
    11. 5605
    Prev
    Next
    INDEX
    Explanations

    structured programming syntax involving control flow and data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "cur" followed by a hexadecimal value

    np_acts-logits-general · gemini-2.0-flash

    cur uint16 struct

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Zeller
    -0.63
    andoah
    -0.52
     Vivi
    -0.50
     Alab
    -0.48
     GTO
    -0.48
    توض
    -0.46
     Kom
    -0.46
     diamants
    -0.46
    idl
    -0.46
    Pike
    -0.46
    POSITIVE LOGITS
     CUR
    2.90
     Cur
    2.84
    Cur
    2.74
     cur
    2.70
    cur
    2.62
    CUR
    2.56
     Kur
    2.20
     Curran
    2.08
     Curve
    2.06
    Kur
    2.06
    Activations Density 0.298%

    No Known Activations