© 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. 1356
    Prev
    Next
    INDEX
    Explanations

    references to books or texts and their descriptions

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

    Code documentation and descriptions

    np_acts-logits-general · gemini-2.0-flash

    brief description

    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
     Administrativna
    -0.53
     Taktlose
    -0.50
    liflower
    -0.46
    matchCondition
    -0.45
    ConstraintMaker
    -0.45
    recated
    -0.44
    Geplaatst
    -0.44
    transQ
    -0.44
    dialect
    -0.44
     kaarangay
    -0.44
    POSITIVE LOGITS
     description
    1.69
     Description
    1.43
    description
    1.42
    Description
    1.35
     descriptions
    1.32
     DESCRIPTION
    1.27
     descripción
    1.22
    DESCRIPTION
    1.20
     describe
    1.17
     descrição
    1.16
    Activations Density 0.389%

    No Known Activations