© 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 - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 7224
    Prev
    Next
    INDEX
    Explanations

    terms associated with high quality or texture described as "fine."

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

    "fine"

    np_acts-logits-general · gemini-2.0-flash

    fine quality or precision

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     queſta
    -0.63
    berday
    -0.62
     مشين
    -0.55
     المعيارى
    -0.55
     zitate
    -0.54
    MLLoader
    -0.54
    Étape
    -0.54
     Puerta
    -0.53
     forState
    -0.53
    berdayakan
    -0.53
    POSITIVE LOGITS
     fine
    2.41
    Fine
    2.28
    fine
    2.23
     Fine
    2.23
     FINE
    2.02
    FINE
    1.93
     finer
    1.48
     fines
    1.34
     finos
    1.27
     finely
    1.26
    Activations Density 0.080%

    No Known Activations