© 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. 10603
    Prev
    Next
    INDEX
    Explanations

    instances of the word "the" and its variations in context

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

    Follows "the"

    np_acts-logits-general · gemini-2.0-flash

    defining specific concepts or items

    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
     betweenstory
    -0.46
     fhould
    -0.33
     should
    -0.31
     ſhould
    -0.31
     landet
    -0.31
     directly
    -0.30
     pères
    -0.29
     Should
    -0.29
    TASK
    -0.29
    TestMethod
    -0.29
    POSITIVE LOGITS
    PyExc
    0.61
    nodoc
    0.59
    脚注の使い方
    0.59
     eloquence
    0.57
    oplasts
    0.57
     carvings
    0.56
     stickers
    0.55
    󠁣
    0.54
     ddelweddau
    0.54
     juicy
    0.54
    Activations Density 0.172%

    No Known Activations