© 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. 47840
    Prev
    Next
    INDEX
    Explanations

    sentences with the word "is" and its variations, indicating its role in expressions of identity or description

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

    That's followed by a word

    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
    BufferedWriter
    -0.54
    afficheront
    -0.51
    InitStruct
    -0.50
    ModelList
    -0.48
    GPC
    -0.48
     updateUser
    -0.48
    ScopeManager
    -0.47
    rset
    -0.46
    -------
    -0.46
     loginUser
    -0.45
    POSITIVE LOGITS
     what
    0.50
     why
    0.49
     whats
    0.48
    ⓘ
    0.46
     That
    0.44
    AddTagHelper
    0.44
    どういう
    0.43
    #+#
    0.43
    whats
    0.42
     how
    0.42
    Activations Density 0.029%

    No Known Activations