© 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. 36-GEMMASCOPE-RES-16K
    11. 12975
    Prev
    Next
    INDEX
    Explanations

    the presence of names or terms related to individuals and entities involved in discussions, particularly in contexts associated with law or public figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/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.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AnchorTagHelper
    -0.33
    scrollTo
    -0.31
     est
    -0.31
    await
    -0.30
    Telefon
    -0.29
     rusty
    -0.29
    shop
    -0.28
    рец
    -0.28
     shop
    -0.28
     ab
    -0.27
    POSITIVE LOGITS
    Personendaten
    0.78
     esternos
    0.63
    Ari
    0.61
    orianCalendar
    0.60
    SBATCH
    0.59
    ri
    0.57
     Ari
    0.56
     незавершена
    0.54
     increí
    0.53
    arashtra
    0.53
    Activations Density 0.242%

    No Known Activations