© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 19-GEMMASCOPE-RES-16K
    11. 15320
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate suspicion or unusual behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AutoScaleMode
    -0.72
    Successfully
    -0.65
    SOUNDBITE
    -0.63
    tvguidetime
    -0.62
    felizmente
    -0.59
    aplic
    -0.59
    findpost
    -0.58
    InjectAttribute
    -0.57
    ArgsConstructor
    -0.57
     GlobalKey
    -0.55
    POSITIVE LOGITS
     suspicious
    2.05
     suspiciously
    1.66
     strange
    1.54
    Suspicious
    1.53
     suspect
    1.47
     unusual
    1.44
     suspic
    1.43
     suspicion
    1.42
     suspicions
    1.41
     sospe
    1.37
    Activations Density 0.417%

    No Known Activations