© 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. 123032
    Prev
    Next
    INDEX
    Explanations

    phrases indicating relationships between concepts or actions

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

    prepositions followed by definite articles

    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
     CreateTagHelper
    -0.91
    tagHelperRunner
    -0.84
    niſſe
    -0.83
     الحره
    -0.83
     للاسماء
    -0.80
    ########.
    -0.78
    <unused52>
    -0.77
    <unused74>
    -0.76
    <unused47>
    -0.76
    <unused28>
    -0.76
    POSITIVE LOGITS
     étant
    0.35
     commerces
    0.33
     itself
    0.33
     being
    0.32
     proyección
    0.31
     négociations
    0.31
     secar
    0.31
     is
    0.31
    における
    0.30
     migrantes
    0.29
    Activations Density 0.162%

    No Known Activations