© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 13815
    Prev
    Next
    INDEX
    Explanations

    phrases indicating actions or events that involve creation, filing, or assessment processes

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

    Perfect tense verbs/verb phrases

    np_acts-logits-general · gemini-2.0-flash

    past tense completed actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
     беше
    -0.36
    ագրություններ
    -0.36
    往下
    -0.35
     nästa
    -0.35
    Exact
    -0.34
    yre
    -0.33
    Finish
    -0.33
     WHEN
    -0.33
    ại
    -0.33
     Werk
    -0.32
    POSITIVE LOGITS
     been
    0.75
     Been
    0.68
    Been
    0.68
     recentemente
    0.65
    been
    0.65
    HasBeen
    0.65
     sinds
    0.63
    ScopeManager
    0.62
     depuis
    0.61
     consultato
    0.61
    Activations Density 0.780%

    No Known Activations