© 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-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 10870
    Prev
    Next
    INDEX
    Explanations

    persistence of sentences and scholarly citations in text

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

    Punctuation followed by specific articles/prepositions

    np_acts-logits-general · gemini-2.0-flash

    interlinking or academic fields

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Anyway
    -0.85
     Maybe
    -0.83
    Anyway
    -0.81
    maybe
    -0.79
     maybe
    -0.79
    Maybe
    -0.76
    anyway
    -0.75
    obviously
    -0.74
     Anyways
    -0.72
    sorry
    -0.71
    POSITIVE LOGITS
     illustrationer
    0.52
     využí
    0.46
     while
    0.46
     באמצעות
    0.45
    ながら
    0.45
     zejména
    0.44
    mektedir
    0.43
     throughout
    0.43
    Throughout
    0.43
     Throughout
    0.43
    Activations Density 1.310%

    No Known Activations