© 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-2-9B
    7. Residual Stream - 16k
    9. 37-GEMMASCOPE-RES-16K
    11. 6221
    Prev
    Next
    INDEX
    Explanations

    the repeated use of the word "again" indicating a theme of recurrence or repetition in the narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     igjen
    -0.59
    Билгалдахарш
    -0.49
     again
    -0.46
     artık
    -0.46
    genuine
    -0.45
    まま
    -0.44
    contentLoaded
    -0.43
    RTEX
    -0.42
    Arrangement
    -0.41
     aún
    -0.41
    POSITIVE LOGITS
    AndEndTag
    0.49
    s
    0.49
    sth
    0.44
    FirstResponder
    0.41
     rootReducer
    0.40
    sidemargin
    0.39
    nEnter
    0.38
    RectangleBorder
    0.38
    もや
    0.38
     reiter
    0.37
    Activations Density 0.076%

    No Known Activations