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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 1044
    Prev
    Next
    INDEX
    Explanations

    terms related to speed and rapidity

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

    speed or acceleration

    np_acts-logits-general · gemini-2.0-flash

    speed, quickness, acceleration

    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
    exitRule
    -0.59
    outState
    -0.55
    (___
    -0.46
    ngrx
    -0.46
    DataMember
    -0.46
    gdala
    -0.44
     Laub
    -0.43
     behalf
    -0.40
    prüche
    -0.40
    versies
    -0.40
    POSITIVE LOGITS
    Fast
    0.91
    Rapid
    0.89
     Fast
    0.88
    rapid
    0.86
     FAST
    0.86
    FAST
    0.85
     rapides
    0.84
    Speed
    0.84
     fast
    0.84
     Speedy
    0.83
    Activations Density 0.165%

    No Known Activations