© 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. 18-GEMMASCOPE-RES-16K
    11. 14983
    Prev
    Next
    INDEX
    Explanations

    references to confidentiality and personal information privacy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    secrecy or confidentiality

    np_acts-logits-general · gemini-2.0-flash

    confidentiality and secrecy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    retweeted
    -0.59
     بيها
    -0.58
    tonode
    -0.56
     كمان
    -0.54
     palsy
    -0.54
    ChildScrollView
    -0.53
     interp
    -0.53
    Personensuche
    -0.53
    ότη
    -0.53
    lioz
    -0.53
    POSITIVE LOGITS
     secret
    2.23
     secrecy
    2.23
     confidentiality
    1.98
     confidential
    1.97
    secret
    1.93
     secretive
    1.92
     privacy
    1.85
     Secret
    1.82
     hidden
    1.81
    Secret
    1.74
    Activations Density 0.709%

    No Known Activations