© 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. 6712
    Prev
    Next
    INDEX
    Explanations

    elements related to visual imagery and creative expression in various contexts

    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
    The
    -0.40
    I
    -0.40
     동안
    -0.39
    enumi
    -0.38
    You
    -0.37
     emple
    -0.34
     composants
    -0.34
     Unternehmens
    -0.34
     bandera
    -0.33
     usually
    -0.33
    POSITIVE LOGITS
    iſen
    0.73
    ſcher
    0.71
    majánló
    0.69
     autorytatywna
    0.69
    ']?>
    0.66
     vooz
    0.66
    iſter
    0.65
    mpagne
    0.65
    MENAFN
    0.64
     Geiſt
    0.63
    Activations Density 0.765%

    No Known Activations