© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 5603
    Prev
    Next
    INDEX
    Explanations

    specific names of individuals associated with academic or scientific contexts

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

    before numbers or symbols

    np_acts-logits-general · gemini-2.0-flash

    names and universities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MLLoader
    -0.75
    jsxFileName
    -0.75
    principalColumn
    -0.74
     パンチラ
    -0.73
    <unused41>
    -0.73
    <pad>
    -0.73
    <unused43>
    -0.73
    <unused74>
    -0.73
    <unused42>
    -0.73
    <unused23>
    -0.73
    POSITIVE LOGITS
      
    0.40
    🐷
    0.34
     The
    0.33
     admitted
    0.32
    se
    0.32
    ↵
    0.31
     Unfortunately
    0.31
     Schweden
    0.31
    Deutschland
    0.31
    The
    0.30
    Activations Density 0.433%

    No Known Activations