© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 14217
    Prev
    Next
    INDEX
    Explanations

    future events or actions that are anticipated to happen soon

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

    "soon" and its translations

    np_acts-logits-general · gemini-2.0-flash

    soon followed by events

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    casila
    -0.44
    atyw
    -0.43
    mybatisplus
    -0.41
     danych
    -0.41
     controllare
    -0.40
     africains
    -0.40
    menuStrip
    -0.39
     text
    -0.39
    ajuku
    -0.39
     noires
    -0.39
    POSITIVE LOGITS
    Soon
    1.23
     Soon
    1.17
    soon
    1.12
     soon
    1.12
     SOON
    1.00
    🔜
    0.81
     foon
    0.77
    ientôt
    0.76
     скоро
    0.71
     snart
    0.71
    Activations Density 0.056%

    No Known Activations