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. 92568
    Prev
    Next
    INDEX
    Explanations

    words and phrases indicating existence or presence

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

    scientific and technical terms

    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
     estuvieron
    -0.23
    ंटर
    -0.21
    bitField
    -0.21
     habrían
    -0.20
    Tembelea
    -0.20
     termasuk
    -0.20
    EnumMember
    -0.19
    avais
    -0.19
    最
    -0.17
     poursuite
    -0.17
    POSITIVE LOGITS
    
    0.81
    SourceChecksum
    0.81
    bootstrapcdn
    0.79
     queſto
    0.79
    ſammen
    0.78
    󠀠
    0.77
     ſoll
    0.76
     zwiſchen
    0.76
     kaarangay
    0.75
     ويكيپ
    0.74
    Activations Density 0.162%

    No Known Activations