© 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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 107230
    Prev
    Next
    INDEX
    Explanations

    elements of coding syntax and function calls in a programming context

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

    closing parenthesis usage in code/plots

    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
     autorytatywna
    -0.72
     zuſammen
    -0.67
     témoig
    -0.65
    IUrlHelper
    -0.63
    RTEE
    -0.60
     JAXBElement
    -0.60
     useCallback
    -0.60
    <unused74>
    -0.60
     متعلقه
    -0.59
     zwiſchen
    -0.59
    POSITIVE LOGITS
    VYMaps
    0.41
    AutoScale
    0.33
     Decke
    0.30
    EditPart
    0.30
     disambiguazione
    0.29
    muerzo
    0.29
    󠁴
    0.29
     Trä
    0.28
    hashtags
    0.27
    tersebut
    0.27
    Activations Density 0.011%

    No Known Activations