© 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
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 2331
    Prev
    Next
    INDEX
    Explanations

    specific nouns and their attributes related to evidence and investigation

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

    specific numerical or numerical-adjacent details (percentages, years, count of things, measurements).

    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
     constitución
    -0.46
     Italij
    -0.45
     asegurarse
    -0.45
     Constitución
    -0.44
     traseiro
    -0.43
     conclusión
    -0.43
     adquis
    -0.43
     Voraussetzung
    -0.42
     convierten
    -0.42
     Sünde
    -0.42
    POSITIVE LOGITS
     Meksiku
    0.65
    ьаж
    0.65
     betweenstory
    0.63
     հղումներ
    0.61
     other
    0.59
     tartalomajánló
    0.57
    utilisons
    0.57
    rungsseite
    0.57
     spat
    0.56
    ftagPool
    0.56
    Activations Density 0.500%

    No Known Activations