© 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. 15-GEMMASCOPE-RES-16K
    11. 3006
    Prev
    Next
    INDEX
    Explanations

    phrases related to defense mechanisms and vulnerabilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GeneratedMessage
    -0.64
    новниш
    -0.56
    NameInMap
    -0.55
     OMIT
    -0.53
    Importante
    -0.53
    UseVisualStyle
    -0.49
     Wikimedijinoj
    -0.49
    elfth
    -0.49
    astéroïdes
    -0.49
    trak
    -0.49
    POSITIVE LOGITS
     toughest
    0.74
     defeat
    0.72
     insurmountable
    0.70
     resistance
    0.69
     resistant
    0.68
     defeats
    0.67
     defeating
    0.66
    resistant
    0.64
     defeated
    0.64
    resistance
    0.63
    Activations Density 0.316%

    No Known Activations