© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 5777
    Prev
    Next
    INDEX
    Explanations

    conversational elements and discussions around film and artistic expression

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

    references to specific people, particularly in interviews or biographical contexts.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
    دانشنامهٔ
    -0.56
    featureID
    -0.50
     cherchés
    -0.48
     referenties
    -0.44
     drog
    -0.43
    Koordinaten
    -0.43
    VideoCapture
    -0.42
    MessageState
    -0.41
     חיצוניים
    -0.41
     références
    -0.41
    POSITIVE LOGITS
     Lleva
    0.41
     Gerechtigkeit
    0.41
    ="@+
    0.41
    onaceous
    0.40
    OrCreate
    0.40
     rumahnya
    0.40
     chapéu
    0.39
     Ră
    0.39
     creator
    0.39
    イクアウト
    0.38
    Activations Density 0.097%

    No Known Activations