© 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-2-9B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 2124
    Prev
    Next
    INDEX
    Explanations

    references to a specific individual or character, particularly identified by the pronoun "her."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ViewFeatures
    -0.49
     intptr
    -0.45
    BeginContext
    -0.45
     Numerade
    -0.40
     cục
    -0.39
     Италијани
    -0.39
     старости
    -0.39
     Castelo
    -0.38
     miniaturka
    -0.38
    Controllo
    -0.38
    POSITIVE LOGITS
    Her
    2.81
     Her
    2.80
     HER
    2.67
    her
    2.64
    HER
    2.58
     her
    2.39
     Herb
    1.85
    Herb
    1.77
    herb
    1.76
     herb
    1.73
    Activations Density 0.398%

    No Known Activations