© 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. 24-GEMMASCOPE-RES-16K
    11. 7687
    Prev
    Next
    INDEX
    Explanations

    actions and states related to teaching and assistance

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

    Verb followed by "her."

    np_acts-logits-general · gemini-2.0-flash

    verbs followed by her

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     she
    -1.06
    she
    -0.95
     herself
    -0.93
    herself
    -0.91
     оно
    -0.87
    writeFieldEnd
    -0.85
    AutoScaleMode
    -0.81
    esModule
    -0.77
    She
    -0.74
     hän
    -0.74
    POSITIVE LOGITS
     her
    1.60
    her
    0.90
     them
    0.80
     HER
    0.76
    Her
    0.70
     ihr
    0.65
     him
    0.63
     Her
    0.63
     herr
    0.61
     ber
    0.61
    Activations Density 0.155%

    No Known Activations