© 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. 11212
    Prev
    Next
    INDEX
    Explanations

    concepts related to key-value pairs and their relationships within a structured format

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

    pairs or couples

    np_acts-logits-general · gemini-2.0-flash

    pair or couple

    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
     trưng
    -0.48
     handleMessage
    -0.48
    zież
    -0.47
    ControllerAdvice
    -0.47
    uguetes
    -0.45
    IsContent
    -0.45
     VizieR
    -0.45
    vânt
    -0.45
     HasFactory
    -0.43
     FSM
    -0.43
    POSITIVE LOGITS
     pair
    3.14
     pairs
    2.68
     Pair
    2.67
    pair
    2.65
     duo
    2.52
    Pair
    2.50
     Pairs
    2.38
     PAIR
    2.33
     couple
    2.32
     paire
    2.31
    Activations Density 0.575%

    No Known Activations