© 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. 23-GEMMASCOPE-RES-16K
    11. 3883
    Prev
    Next
    INDEX
    Explanations

    details related to specific geometric dimensions and configurations of a structure or device

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/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.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ige
    -0.38
    iint
    -0.36
    iLocal
    -0.35
    uParam
    -0.34
     sph
    -0.32
     Blatt
    -0.32
     Stell
    -0.31
    FillColor
    -0.31
     Pri
    -0.31
     spherical
    -0.31
    POSITIVE LOGITS
     length
    0.89
     panjang
    0.88
     lengths
    0.86
     longueur
    0.84
     Length
    0.81
     sepanjang
    0.80
     Panjang
    0.79
    panjang
    0.78
    itudinal
    0.77
     lengthwise
    0.74
    Activations Density 1.208%

    No Known Activations