© 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. 11076
    Prev
    Next
    INDEX
    Explanations

    specific formatting and editorial requirements in a review process

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

    Formalities, requests, or minor issues

    np_acts-logits-general · gemini-2.0-flash

    various items

    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
    Personendaten
    -0.45
     AVAILABILITY
    -0.38
    localVar
    -0.33
     يتيمه
    -0.32
    ьажоргаш
    -0.32
     quedará
    -0.31
    raseña
    -0.30
     Meksiku
    -0.30
     disponibilidad
    -0.30
     Sollte
    -0.30
    POSITIVE LOGITS
    各项
    0.86
     vieles
    0.83
     numerous
    0.81
    色々と
    0.79
     many
    0.75
     items
    0.73
     features
    0.73
     various
    0.73
    的一些
    0.72
    诸多
    0.72
    Activations Density 0.918%

    No Known Activations