© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 10839
    Prev
    Next
    INDEX
    Explanations

    terms related to pipelines and structured data organization in various contexts

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

    Lists or sets of items

    np_acts-logits-general · gemini-2.0-flash

    lists and collections

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     Psychological
    -0.45
     Pedro
    -0.44
    Fernseh
    -0.43
     Singer
    -0.42
     Flower
    -0.42
     Bird
    -0.42
     Potato
    -0.42
     Lonely
    -0.41
     noDo
    -0.41
    withdrawal
    -0.41
    POSITIVE LOGITS
     repertoire
    0.62
    pertoire
    0.56
     portfolio
    0.55
    chequer
    0.52
    ortiment
    0.51
     inventario
    0.51
    ventory
    0.51
    protoimpl
    0.50
     lijst
    0.50
    inerary
    0.50
    Activations Density 0.873%

    No Known Activations