Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 40698
    Prev
    Next
    INDEX
    Explanations

    frequency of the word "mit" and similar connecting words across different contexts

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

    preposition of accompaniment/connection

    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
     enfans
    -0.64
     houſe
    -0.52
    strokeColor
    -0.49
     pleaſure
    -0.49
     plufieurs
    -0.47
     marbre
    -0.47
    publicPath
    -0.47
     honneur
    -0.46
     Grecs
    -0.45
     rasg
    -0.44
    POSITIVE LOGITS
    with
    1.05
    With
    0.97
     WITH
    0.96
    WITH
    0.94
     With
    0.88
     avec
    0.85
     dengan
    0.84
    Avec
    0.83
     with
    0.82
     עם
    0.82
    Activations Density 0.003%

    No Known Activations