© 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. 28-GEMMASCOPE-RES-16K
    11. 8289
    Prev
    Next
    INDEX
    Explanations

    references to transition metals and their compounds

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

    Metal ions or sulfides

    np_acts-logits-general · gemini-2.0-flash

    zinc and copper compounds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Atsauces
    -0.39
     yks
    -0.32
     робити
    -0.30
     tehdä
    -0.30
     chấm
    -0.29
     käyttää
    -0.29
     spraw
    -0.29
     Maker
    -0.29
     prière
    -0.29
     Karls
    -0.28
    POSITIVE LOGITS
     ComVisible
    0.74
    istoitu
    0.62
     pinulongan
    0.60
    CppMethod
    0.59
    aluminium
    0.59
     aluminium
    0.58
    aluminum
    0.58
    الإنجليزية
    0.57
     aluminum
    0.56
     Aluminium
    0.56
    Activations Density 0.374%

    No Known Activations