© 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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 105647
    Prev
    Next
    INDEX
    Explanations

    references to institutional or formal entities

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

    recognizes contributions to science; languages

    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
    TagMode
    -0.49
    Spoljašnje
    -0.44
    Jeografia
    -0.42
    nlm
    -0.41
    lankton
    -0.41
    httphttps
    -0.41
     Arms
    -0.40
    цездатний
    -0.40
    ruhe
    -0.40
     Otter
    -0.40
    POSITIVE LOGITS
     insuffisamment
    0.56
    CloseOperation
    0.47
     AssemblyCompany
    0.43
     Suiza
    0.43
     Espanha
    0.42
    GOTREF
    0.42
    berdayakan
    0.42
     asimismo
    0.41
    存于互联网档案馆
    0.41
     likewise
    0.40
    Activations Density 0.072%

    No Known Activations