© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 8-GEMMASCOPE-RES-16K
    11. 7824
    Prev
    Next
    INDEX
    Explanations

    terms and phrases associated with stealth or covert actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     فريبيس
    -0.74
    RegistryLite
    -0.67
     يتيمه
    -0.66
     PublicKey
    -0.65
    neat
    -0.62
    Numerology
    -0.61
     ſtre
    -0.60
     ſhe
    -0.59
     Pristupljeno
    -0.59
     juſ
    -0.59
    POSITIVE LOGITS
    ]^{-
    0.51
     settle
    0.48
    ros
    0.42
    дайте
    0.41
    canestro
    0.41
    Defs
    0.41
    nsa
    0.40
     Jump
    0.40
    Biographies
    0.40
    sitive
    0.39
    Activations Density 0.154%

    No Known Activations