© 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. 13008
    Prev
    Next
    INDEX
    Explanations

    concepts related to safety and risks in social and romantic interactions

    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
     iprot
    -0.58
     ligiloj
    -0.56
    errHandler
    -0.55
    DispatchToProps
    -0.55
    unhofer
    -0.54
    SharedCtor
    -0.53
    empereur
    -0.52
    StoryboardSegue
    -0.52
    SpringBootTest
    -0.52
     Thebes
    -0.52
    POSITIVE LOGITS
     security
    0.82
     safety
    0.81
     Safety
    0.76
     unes
    0.75
    Safety
    0.75
    safety
    0.74
    security
    0.74
     Security
    0.72
     SAFETY
    0.68
     unsafe
    0.67
    Activations Density 0.242%

    No Known Activations