Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 12273
    Prev
    Next
    INDEX
    Explanations

    references to security situations and protective measures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCulture
    -0.70
    HostException
    -0.52
     chronique
    -0.49
     freio
    -0.48
     barne
    -0.47
    ImageContext
    -0.46
    enumi
    -0.46
     OnEnable
    -0.45
    DispatchToProps
    -0.45
     terecht
    -0.45
    POSITIVE LOGITS
     security
    1.68
    security
    1.40
     Security
    1.35
    Security
    1.32
     SECURITY
    1.26
     guards
    1.20
     guard
    1.19
     patrols
    1.17
    SECURITY
    1.17
     guarding
    1.15
    Activations Density 0.273%

    No Known Activations