Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 8519
    Prev
    Next
    INDEX
    Explanations

    questions or references to identity

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

    "Who" followed by question words or uncertainty

    np_acts-logits-general · gemini-2.0-flash

    who initiating questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    expandindo
    -0.71
    DataAnnotations
    -0.65
    UnusedPrivate
    -0.58
     ivelany
    -0.53
     Meksiku
    -0.53
     medan
    -0.51
    iyaki
    -0.51
    andExpect
    -0.50
     beginnetje
    -0.50
     lont
    -0.49
    POSITIVE LOGITS
     else
    1.03
     cares
    0.81
     knows
    0.78
     Who
    0.74
     antaranya
    0.71
    Who
    0.71
     Else
    0.71
     ELSE
    0.70
    among
    0.68
     AMONG
    0.67
    Activations Density 0.047%

    No Known Activations