© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14002
    Prev
    Next
    INDEX
    Explanations

    elements and attributes in structured data format, such as code or markup languages

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

    Code or data table related tokens

    np_acts-logits-general · gemini-2.0-flash

    code structure and fields

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     informée
    -0.77
    msgTypes
    -0.68
     Administrativna
    -0.66
    PyExc
    -0.66
     <=",
    -0.65
     мәкал
    -0.65
     contextLoads
    -0.64
    fjspx
    -0.63
    LookAnd
    -0.63
     ويكيميديا
    -0.63
    POSITIVE LOGITS
     sportifs
    0.32
    ambién
    0.32
    gunas
    0.29
     attributes
    0.29
     atribu
    0.28
     information
    0.28
     rambut
    0.28
     demás
    0.28
     contenido
    0.28
     rense
    0.28
    Activations Density 0.219%

    No Known Activations