© 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. 16-GEMMASCOPE-RES-16K
    11. 4871
    Prev
    Next
    INDEX
    Explanations

    references to sets or collections of items or data

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

    "set" or "sets"

    np_acts-logits-general · gemini-2.0-flash

    set of / sets of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    couvrez
    -0.88
    enumii
    -0.84
    SerializedSize
    -0.83
    RESP
    -0.79
     оригіналу
    -0.78
    сылкі
    -0.76
     whiteColor
    -0.72
     MainAxisSize
    -0.72
     GenerationType
    -0.70
    abestanden
    -0.70
    POSITIVE LOGITS
     SET
    1.31
     set
    1.31
     Set
    1.28
    Set
    1.25
    set
    1.21
     sets
    1.15
    SET
    1.14
     Sets
    1.09
    sets
    1.02
     SETS
    0.96
    Activations Density 0.104%

    No Known Activations