© 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. 3-GEMMASCOPE-RES-16K
    11. 12681
    Prev
    Next
    INDEX
    Explanations

    keywords related to safety and security

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onAttach
    -0.84
    WithIOException
    -0.77
    Посилання
    -0.76
    GetMapping
    -0.75
     Abp
    -0.73
    Kontrola
    -0.72
    upol
    -0.71
    ANNES
    -0.71
     Gazetteer
    -0.71
    @[+][
    -0.70
    POSITIVE LOGITS
     safe
    3.40
     Safe
    3.12
    safe
    2.98
    Safe
    2.93
     SAFE
    2.81
    SAFE
    2.62
     safer
    2.26
     safely
    2.19
     safest
    2.13
    saf
    1.89
    Activations Density 0.070%

    No Known Activations