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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 28855
    Prev
    Next
    INDEX
    Explanations

    phrases indicating conditions or qualifications regarding actions or statements

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

    only, few, emphasis, main

    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
    AndEndTag
    -0.70
    帖最后由
    -0.69
    +#+#
    -0.68
    istoitu
    -0.68
    niſſe
    -0.67
    FunctionFlags
    -0.67
     ब्रेकडाउन
    -0.66
    BagConstraints
    -0.66
     AssemblyCulture
    -0.65
     Menſchen
    -0.65
    POSITIVE LOGITS
     rather
    0.41
    rather
    0.30
    而不是
    0.27
     zentralen
    0.27
    Rather
    0.26
     Entwicklungs
    0.26
     próprias
    0.25
    current
    0.24
    ิจ
    0.24
    brengen
    0.24
    Activations Density 0.193%

    No Known Activations