© 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. 20-GEMMASCOPE-RES-16K
    11. 7024
    Prev
    Next
    INDEX
    Explanations

    conditional phrases indicating time or scenarios

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

    Conditional statements ("if", "when", "once")

    np_acts-logits-general · gemini-2.0-flash

    if, when, once

    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
     écout
    -0.48
     admires
    -0.48
    manner
    -0.46
     Biôgrafia
    -0.46
     conferma
    -0.46
     estekak
    -0.44
     bassa
    -0.44
     przede
    -0.44
     realisation
    -0.44
     illuminates
    -0.44
    POSITIVE LOGITS
     they
    1.11
     it
    0.95
     taken
    0.92
     done
    0.87
     you
    0.86
    InputBorder
    0.84
     the
    0.82
     there
    0.77
     we
    0.75
     held
    0.74
    Activations Density 0.265%

    No Known Activations