© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 4963
    Prev
    Next
    INDEX
    Explanations

    terms related to cyber threats and terrorist activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fxml
    -0.35
     CHAT
    -0.31
    [*]
    -0.30
    っこう
    -0.28
    onViewCreated
    -0.28
    inage
    -0.28
     jadx
    -0.28
     Administrative
    -0.28
    Permanent
    -0.28
     Verwaltungs
    -0.28
    POSITIVE LOGITS
     attackers
    0.66
    kháu
    0.63
     препратки
    0.58
    TintMode
    0.57
     crossorigin
    0.56
     invasive
    0.55
    Datuak
    0.55
     invading
    0.54
     attacks
    0.54
     ISIS
    0.54
    Activations Density 1.185%

    No Known Activations