© 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 EvalsExportsinterp-engineNEWAPI 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. 8657
    Prev
    Next
    INDEX
    Explanations

    terminology related to processing and data structures in programming contexts

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

    preceding technical terms

    np_acts-logits-general · gemini-2.0-flash

    data structure or configuration files

    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
     BoxFit
    -0.55
    tagHelper
    -0.53
    RTGC
    -0.51
     ſind
    -0.48
     Quanti
    -0.47
    artis
    -0.47
    pne
    -0.45
     campa
    -0.44
    hists
    -0.44
    ggies
    -0.44
    POSITIVE LOGITS
    MarshalTo
    0.53
     conferencia
    0.45
    UrlResolution
    0.44
     conferencias
    0.41
    PreferredItem
    0.39
     subtitle
    0.39
     financière
    0.39
     enfans
    0.37
     StatefulWidget
    0.37
    CloseOperation
    0.37
    Activations Density 1.197%

    No Known Activations