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. 30373
    Prev
    Next
    INDEX
    Explanations

    actions and evaluative processes related to assessment and decision-making

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

    discusses or asserts a fact

    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
     Lul
    -0.45
     WL
    -0.39
     Pal
    -0.38
     pal
    -0.37
    pal
    -0.37
    書館
    -0.36
     Wod
    -0.36
    彤
    -0.35
    pet
    -0.35
     métier
    -0.35
    POSITIVE LOGITS
     lisäksi
    0.66
    fjspx
    0.63
     dessutom
    0.59
     également
    0.58
     gärna
    0.56
     ayrıca
    0.56
     eventuali
    0.55
    脚注の使い方
    0.54
     myös
    0.53
    Cyfarwyddwr
    0.53
    Activations Density 0.106%

    No Known Activations