© 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 EvalsExportsinterp-engineNEWAPI 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. 10988
    Prev
    Next
    INDEX
    Explanations

    phrases related to societal issues and narratives about race and privilege

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

    Follows "Q:" or "of"

    np_acts-logits-general · gemini-2.0-flash

    identification of

    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
     feroit
    -0.90
     pouvoit
    -0.89
     auroit
    -0.87
     Chriftian
    -0.85
     étoient
    -0.84
     étoit
    -0.84
     oprot
    -0.82
     avoient
    -0.80
     enfans
    -0.79
    SourceChecksum
    -0.79
    POSITIVE LOGITS
     even
    0.79
    </thead>
    0.58
     sogar
    0.55
     etc
    0.54
     Even
    0.52
    何より
    0.51
     s
    0.50
     hatta
    0.50
     des
    0.49
     zelfs
    0.49
    Activations Density 0.374%

    No Known Activations