© 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 - 131k
    5. 24-GEMMASCOPE-RES-131K
    6. 403
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    sibilità
    -0.45
     MATER
    -0.45
     Mater
    -0.43
     automat
    -0.42
    MATER
    -0.42
     Cymru
    -0.42
    RTEE
    -0.41
     collectors
    -0.41
    atecas
    -0.41
     keys
    -0.41
    POSITIVE LOGITS
    TextAppearance
    0.94
    PMailer
    0.51
     TextAppearance
    0.46
     CreateTagHelper
    0.44
     kasarigan
    0.41
     مرئيه
    0.40
     للمعارف
    0.39
    település
    0.39
    WriteLiteral
    0.38
    lím
    0.38
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.