© 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. 14-GEMMASCOPE-RES-16K
    11. 6226
    Prev
    Next
    INDEX
    Explanations

    boolean values indicating conditions or states within a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cass
    -0.82
    ConstraintMaker
    -0.72
     deſſen
    -0.71
     beſch
    -0.71
     verſch
    -0.69
    ///
    -0.69
    RTEX
    -0.68
     cass
    -0.67
     témoig
    -0.67
    tshell
    -0.66
    POSITIVE LOGITS
     true
    1.31
    true
    1.28
    True
    1.23
     True
    1.19
     TRUE
    1.04
    TRUE
    1.03
    assertTrue
    0.77
     verdadera
    0.75
    stdbool
    0.74
     verdadero
    0.73
    Activations Density 0.049%

    No Known Activations