© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 6344
    Prev
    Next
    INDEX
    Explanations

    technical terms related to skills and capabilities in a specific context

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

    Voyager mecha alternate arrangements

    np_acts-logits-general · gemini-2.0-flash

    alternate arrangement composed

    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
    httphttps
    -0.69
     autorytatywna
    -0.66
    UserScript
    -0.65
    fromnode
    -0.63
     betweenstory
    -0.56
    GIVEREF
    -0.55
    adaptiveStyles
    -0.53
     kaarangay
    -0.51
     beginnetje
    -0.50
    RTEE
    -0.49
    POSITIVE LOGITS
     contrats
    0.56
     anillos
    0.50
     indirectly
    0.48
     Italij
    0.47
     muebles
    0.46
     giras
    0.46
     Desarrollo
    0.45
     parís
    0.45
     ebenfalls
    0.44
     orejas
    0.44
    Activations Density 1.035%

    No Known Activations