© 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. 121865
    Prev
    Next
    INDEX
    Explanations

    format specifiers and patterns related to logging or output formatting in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    TagMode
    -0.45
    Atsauces
    -0.44
     estekak
    -0.44
    verwijspagina
    -0.43
     disambiguazione
    -0.40
     nakalista
    -0.36
     <>",
    -0.36
     mümkün
    -0.35
     aans
    -0.35
     ayr
    -0.35
    POSITIVE LOGITS
    AndEndTag
    0.57
    évaluateur
    0.54
    MethodManager
    0.53
    styleType
    0.52
    <unused3>
    0.49
    <unused51>
    0.49
     vVar
    0.49
    <unused42>
    0.49
    <unused16>
    0.49
    <unused28>
    0.49
    Activations Density 0.012%

    No Known Activations