© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 67849
    Prev
    Next
    INDEX
    Explanations

    occurrences of header file inclusions in code snippets

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

    <start_of_turn>user

    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
    يميديا
    -1.03
     disambiguazione
    -0.95
    <unused41>
    -0.92
    <unused8>
    -0.92
    <unused14>
    -0.92
    <unused43>
    -0.91
    <unused51>
    -0.91
    <unused28>
    -0.91
    <unused16>
    -0.91
    <unused23>
    -0.91
    POSITIVE LOGITS
     مه
    0.25
     intermédiaire
    0.21
     hoy
    0.20
     intermediate
    0.20
    intermediate
    0.20
     selection
    0.20
     chrétien
    0.20
     ditu
    0.20
                     
    0.20
    了出来
    0.20
    Activations Density 0.008%

    No Known Activations