© 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. 6700
    Prev
    Next
    INDEX
    Explanations

    code syntax related to control structures and function definitions

    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
     faſt
    -0.67
    enderror
    -0.65
    ſelf
    -0.63
     ſta
    -0.62
     againſt
    -0.57
     fubject
    -0.57
     Majefty
    -0.57
     ་་
    -0.56
    存于互联网档案馆
    -0.56
     Verſ
    -0.55
    POSITIVE LOGITS
     the
    0.41
     an
    0.40
     konden
    0.38
    the
    0.36
    The
    0.36
    withIdentifier
    0.36
    하면
    0.35
    頃は
    0.35
     rechnen
    0.35
     puissiez
    0.34
    Activations Density 0.077%

    No Known Activations