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. 28102
    Prev
    Next
    INDEX
    Explanations

    concepts related to personal choice and subjective decision-making

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

    discretion depends on context

    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
    bootstrapcdn
    -0.61
    prefixer
    -0.60
    ፩
    -0.57
     linkovi
    -0.55
     noDo
    -0.54
    __':
    -0.51
     <=",
    -0.50
    moveToFirst
    -0.49
    ajuato
    -0.48
    Démographie
    -0.48
    POSITIVE LOGITS
    angkut
    0.38
     whether
    0.36
    ea
    0.35
     Leute
    0.35
    ta
    0.34
    dec
    0.34
    paramInt
    0.34
     pungkasnya
    0.34
     decision
    0.33
    hisattva
    0.33
    Activations Density 0.031%

    No Known Activations