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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 64896
    Prev
    Next
    INDEX
    Explanations

    key concepts related to various aspects of everyday life and societal issues

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

    concepts and their descriptions

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     дописавши
    -0.46
     Chancen
    -0.42
     olmayan
    -0.42
    drawSprites
    -0.42
     يتيمه
    -0.41
     незавершена
    -0.40
    مقاله
    -0.40
    einf
    -0.40
    HomeAsUpEnabled
    -0.40
     couvercle
    -0.39
    POSITIVE LOGITS
    enderror
    0.52
     Buda
    0.45
    ysacchar
    0.45
     DDR
    0.44
    httphttps
    0.44
     dj
    0.44
     Resident
    0.43
     Buck
    0.42
     NOI
    0.42
     gyhoeddwyd
    0.42
    Activations Density 0.080%

    No Known Activations