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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 5295
    Prev
    Next
    INDEX
    Explanations

    elements related to procedural actions and decision-making in various contexts

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

    Something is pending "until" a condition

    np_acts-logits-general · gemini-2.0-flash

    continue until

    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
     Италијани
    -0.79
     MainAxisSize
    -0.73
    коменду
    -0.67
     '\\;'
    -0.66
    脚注の使い方
    -0.66
    esgue
    -0.65
    ỡng
    -0.65
    cantara
    -0.65
    |}{$
    -0.64
    Verdana
    -0.61
    POSITIVE LOGITS
     until
    4.08
    until
    3.61
     Until
    3.47
    Until
    3.43
     UNTIL
    3.18
     till
    3.09
     untill
    3.02
    直到
    2.63
     hasta
    2.60
     jusqu
    2.57
    Activations Density 1.351%

    No Known Activations