© 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. 11259
    Prev
    Next
    INDEX
    Explanations

    phrases that refer to the "front" of various objects or 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
    JSONException
    -0.52
     Wiktionnaire
    -0.45
     lagu
    -0.40
    escolar
    -0.40
     Préférences
    -0.40
    лятор
    -0.38
    かわらず
    -0.37
     المثال
    -0.36
     malattia
    -0.36
    volmente
    -0.36
    POSITIVE LOGITS
     front
    1.18
    Front
    1.16
    front
    1.13
     Front
    1.13
     FRONT
    1.09
    FRONT
    1.05
    ront
    0.84
     fronts
    0.82
     frontend
    0.79
     frontline
    0.77
    Activations Density 0.095%

    No Known Activations