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. 56616
    Prev
    Next
    INDEX
    Explanations

    cooking-related actions and ingredients

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

    water bath

    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
     AssemblyCulture
    -0.75
     autorytatywna
    -0.62
     noDo
    -0.60
     nahilalakip
    -0.56
    InputTagHelper
    -0.53
     arşivlendi
    -0.52
    VYMaps
    -0.50
    principalColumn
    -0.49
    Datuak
    -0.48
     paff
    -0.48
    POSITIVE LOGITS
    LabelTagHelper
    0.42
    databinding
    0.40
    المكان
    0.36
    spyOn
    0.35
     cejas
    0.33
    줌
    0.33
    ☚
    0.32
    gelopen
    0.32
    OSPITAL
    0.32
     mastered
    0.32
    Activations Density 0.014%

    No Known Activations