© 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. 96485
    Prev
    Next
    INDEX
    Explanations

    future tense verbs or phrases indicating likelihood or obligation

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

    future tense verbs across languages

    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
     mijne
    -0.51
     chrétien
    -0.45
     zijne
    -0.39
     odpově
    -0.39
     proteção
    -0.37
     universel
    -0.36
     nær
    -0.36
     Weisheit
    -0.36
     intérieure
    -0.35
    sumber
    -0.35
    POSITIVE LOGITS
     will
    0.92
     be
    0.87
    Akan
    0.81
    还会
    0.78
     sẽ
    0.78
    will
    0.78
    OGND
    0.77
    会
    0.76
     会
    0.76
     akan
    0.75
    Activations Density 0.001%

    No Known Activations