© 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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 12347
    Prev
    Next
    INDEX
    Explanations

    references to different versions or variants of a subject

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

    "version" or its translations and variants

    np_acts-logits-general · gemini-2.0-flash

    version and variant

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vectorielles
    -0.40
     Pri
    -0.35
     vectorielle
    -0.35
    Stride
    -0.31
    Pri
    -0.31
    dcterms
    -0.29
    Tut
    -0.28
     enfans
    -0.28
     Tut
    -0.27
    xlabel
    -0.27
    POSITIVE LOGITS
     version
    1.29
     versions
    1.24
     variant
    1.19
     versão
    1.16
     versión
    1.12
     versione
    1.11
     versiones
    1.10
     variants
    1.09
     Variante
    1.07
     Versions
    1.06
    Activations Density 1.270%

    No Known Activations