© 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
    4. Residual Stream - 16k
    5. 38-GEMMASCOPE-RES-16K
    6. 9918
    Prev
    Next
    INDEX
    Explanations

    action verbs related to knowledge, understanding, and decision-making

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     оно
    -0.86
     Оно
    -0.82
     esso
    -0.70
    それが
    -0.68
    Its
    -0.67
    それを
    -0.67
    これを
    -0.64
    它的
    -0.63
    它是
    -0.62
     он
    -0.60
    POSITIVE LOGITS
     Budaya
    0.50
    ihnachts
    0.48
     disambiguazione
    0.47
     Allein
    0.46
     Walkover
    0.45
     Wünsche
    0.44
     Comprometido
    0.44
     Kebijakan
    0.43
    ilarang
    0.43
    atasaray
    0.43
    Activations Density 0.236%

    No Known Activations