© 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-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 11695
    Prev
    Next
    INDEX
    Explanations

    terms associated with secrecy or hidden information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     springfox
    -0.72
    NameInMap
    -0.72
     AllMovie
    -0.71
    DeleteBehavior
    -0.71
     становника
    -0.70
    providers
    -0.69
    Pray
    -0.66
    boldsymbol
    -0.66
     surla
    -0.65
     Hanley
    -0.65
    POSITIVE LOGITS
     secret
    2.92
     Secret
    2.85
    Secret
    2.82
    secret
    2.70
     SECRET
    2.61
     secrets
    2.44
    SECRET
    2.26
     Secrets
    2.20
    Secrets
    2.03
    secrets
    2.00
    Activations Density 0.060%

    No Known Activations