© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 549
    Prev
    Next
    INDEX
    Explanations

    phrases related to recommendations or guidelines

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

    references to urgency or the importance of timing in decision-making

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

    last resort, last straw

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    __":
    -0.72
    endphp
    -0.69
     Pingback
    -0.65
     discovered
    -0.63
     discovers
    -0.61
    <?
    -0.61
    stdafx
    -0.60
     nahilalakip
    -0.59
    __':
    -0.58
     scoperto
    -0.57
    POSITIVE LOGITS
     last
    1.94
    last
    1.66
    Last
    1.65
     Last
    1.59
     LAST
    1.52
     dernier
    1.32
     último
    1.31
    LAST
    1.27
     última
    1.25
     dernière
    1.20
    Activations Density 0.037%

    No Known Activations