© 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. 8882
    Prev
    Next
    INDEX
    Explanations

    references to cookies, user preferences, and their management on websites

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

    constant or continuous states

    np_acts-logits-general · gemini-2.0-flash

    always on

    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
    눠
    -0.27
    τιά
    -0.26
     ago
    -0.26
    を経て
    -0.25
    za
    -0.25
    etten
    -0.24
    läufe
    -0.24
    ft
    -0.24
    pa
    -0.24
     m
    -0.24
    POSITIVE LOGITS
     constantly
    2.06
     always
    1.90
    always
    1.79
    常に
    1.74
     постоянно
    1.73
     constantemente
    1.73
     constamment
    1.70
     constant
    1.69
     continuously
    1.66
     continually
    1.66
    Activations Density 1.037%

    No Known Activations