© 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. 41-GEMMASCOPE-RES-16K
    11. 7640
    Prev
    Next
    INDEX
    Explanations

    chemical formulas or references to specific chemical compounds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Contexto
    -0.36
    trabajo
    -0.36
     humanidad
    -0.35
    Beijo
    -0.35
     okazji
    -0.35
    ﾟ)
    -0.35
    igreja
    -0.35
     kebijakan
    -0.34
    IVEREF
    -0.34
     dzieci
    -0.33
    POSITIVE LOGITS
    httphttps
    0.56
     &___
    0.53
    AndEndTag
    0.50
    onomie
    0.48
    WithIOException
    0.48
    Dort
    0.47
    eket
    0.45
    veral
    0.45
    llow
    0.44
    sitive
    0.44
    Activations Density 0.242%

    No Known Activations