© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 41-GEMMASCOPE-RES-16K
    11. 11946
    Prev
    Next
    INDEX
    Explanations

    elements related to software assembly information and metadata

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AH
    -1.28
     AA
    -1.28
     AE
    -1.21
     AF
    -1.20
     AJ
    -1.20
     AQ
    -1.19
     AW
    -1.17
     AX
    -1.17
     AO
    -1.16
     AK
    -1.15
    POSITIVE LOGITS
    úgó
    0.34
    humanité
    0.30
    indépendance
    0.30
    extérieur
    0.29
    WriteTagHelper
    0.29
    endpush
    0.29
    équilibre
    0.28
    Irlande
    0.28
    essentiel
    0.28
    identité
    0.28
    Activations Density 4.278%

    No Known Activations