© 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
    7. Residual Stream - 16k
    9. 38-GEMMASCOPE-RES-16K
    11. 8739
    Prev
    Next
    INDEX
    Explanations

    specific names, terms or identifiers related to people, organizations, and other proper nouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NewUrlParser
    -0.46
     Efq
    -0.42
     purpoſe
    -0.41
     Nicolson
    -0.40
     Majefty
    -0.40
     NSD
    -0.39
     transférez
    -0.39
     NSM
    -0.39
     psp
    -0.39
    mögen
    -0.39
    POSITIVE LOGITS
     Hollis
    0.91
    iris
    0.88
    IRIS
    0.87
     Janis
    0.83
     IRIS
    0.82
     Doris
    0.80
     Abbas
    0.79
    ellis
    0.79
    Doris
    0.79
     Ferris
    0.79
    Activations Density 1.109%

    No Known Activations