© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 27971
    Prev
    Next
    INDEX
    Explanations

    various punctuation marks and special characters used in written text

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

    rendered in conformance with

    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
     utafitiHapana
    -0.69
    rungsseite
    -0.67
    IsMutable
    -0.64
    таратура
    -0.64
    AndEndTag
    -0.63
    Jeografia
    -0.62
    出版年
    -0.59
     للمعارف
    -0.58
     AssemblyCulture
    -0.58
    قایناقلار
    -0.57
    POSITIVE LOGITS
    WriteTagHelper
    0.34
     smart
    0.28
     basket
    0.28
    望
    0.28
    CascadeType
    0.28
    ができる
    0.27
    mocks
    0.27
    dubbo
    0.27
    woli
    0.27
     sti
    0.26
    Activations Density 0.016%

    No Known Activations