© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 34-GEMMASCOPE-RES-16K
    6. 10898
    Prev
    Next
    INDEX
    Explanations

    instances of the word "between" and its variations, indicating focus on comparisons or relationships within contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ValueStyle
    -0.40
    Remarque
    -0.35
     ejus
    -0.34
    ulemon
    -0.33
    Otro
    -0.33
     conséquences
    -0.33
    dasarkan
    -0.32
     Mühe
    -0.32
    (@"%@",
    -0.31
     kasarigan
    -0.31
    POSITIVE LOGITS
     sexes
    0.88
     Between
    0.86
    Between
    0.83
    between
    0.82
     between
    0.79
     genders
    0.78
    BETWEEN
    0.74
     между
    0.73
     betwixt
    0.71
     BETWEEN
    0.70
    Activations Density 0.123%

    No Known Activations