© 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. 30-GEMMASCOPE-RES-16K
    11. 14843
    Prev
    Next
    INDEX
    Explanations

    components of narratives and their structural elements

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

    Following prepositions/articles

    np_acts-logits-general · gemini-2.0-flash

    categories and sorts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kle
    -0.28
     Im
    -0.27
     im
    -0.26
    fileName
    -0.25
     ה
    -0.25
     Cas
    -0.25
    やっぱ
    -0.24
     Ba
    -0.24
     li
    -0.24
    こんなに
    -0.23
    POSITIVE LOGITS
     sorts
    2.14
     sort
    1.89
    sort
    1.66
     Sort
    1.56
     sorta
    1.53
    Sort
    1.40
     SORT
    1.30
     sortes
    1.18
    kinda
    1.15
     kind
    1.13
    Activations Density 0.256%

    No Known Activations