© 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. 40-GEMMASCOPE-RES-16K
    11. 4387
    Prev
    Next
    INDEX
    Explanations

    terms related to cryptographic keys and security protocols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AddTagHelper
    -0.55
    
    -0.32
    errHandler
    -0.32
    acyjny
    -0.31
    SizeF
    -0.31
    quehanna
    -0.30
    AYSIA
    -0.30
    StoreMessageInfo
    -0.29
    delaide
    -0.29
    kező
    -0.29
    POSITIVE LOGITS
     private
    4.44
     Private
    4.06
    Private
    3.88
     PRIVATE
    3.66
    private
    3.59
    PRIVATE
    3.30
     privately
    3.30
     privado
    3.28
     privada
    3.25
     privat
    3.19
    Activations Density 0.795%

    No Known Activations