© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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 - 131k
    9. 24-GEMMASCOPE-RES-131K
    11. 34
    Prev
    Next
    INDEX
    Explanations

    identifiers and parameters related to coding or data structures

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

    defines and code structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     AssemblyCompany
    -0.58
    msgTypes
    -0.49
    AccessorTable
    -0.44
    Personendaten
    -0.44
    sizeCache
    -0.41
     дописавши
    -0.41
    帖最后由
    -0.40
     niemi
    -0.40
    niversitesi
    -0.39
    
    -0.39
    POSITIVE LOGITS
    Autoritní
    0.60
     Ehrlich
    0.41
     Potential
    0.41
    oa̍t
    0.41
    Архівовано
    0.41
     invokingState
    0.40
     inalámb
    0.40
    IndentedString
    0.40
    Népesség
    0.40
     Wahrheit
    0.40
    Activations Density 0.085%

    No Known Activations