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

    Neuronpedia

    Jacobian LensNEW
    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. 18-GEMMASCOPE-RES-16K
    11. 15320
    Prev
    Next
    INDEX
    Explanations

    phrases and terms associated with suspicion and abnormal behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    doubt or mistrust

    np_acts-logits-general · gemini-2.0-flash

    suspicious and unusual situations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    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
    -0.68
    ReusableCell
    -0.60
    Successfully
    -0.60
    onOptions
    -0.53
    findpost
    -0.52
    successfully
    -0.52
    aplic
    -0.51
     GlobalKey
    -0.49
     successfully
    -0.48
    ButterKnife
    -0.48
    POSITIVE LOGITS
     suspicious
    2.03
     suspiciously
    1.56
     strange
    1.52
    Suspicious
    1.51
     suspicion
    1.47
     suspicions
    1.42
     unusual
    1.41
     suspic
    1.41
     suspect
    1.41
     sospe
    1.39
    Activations Density 0.465%

    No Known Activations