© 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. 35-GEMMASCOPE-RES-16K
    11. 5597
    Prev
    Next
    INDEX
    Explanations

    occurrences of the prefix "Ap" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/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.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Verhältnisse
    -0.41
    contentLoaded
    -0.41
     uważ
    -0.39
     bassa
    -0.37
    іга
    -0.37
     zaś
    -0.36
     blijven
    -0.36
     vinden
    -0.36
     Ceinture
    -0.35
     lopen
    -0.35
    POSITIVE LOGITS
     Ap
    0.71
     AP
    0.64
     Aps
    0.60
     ap
    0.59
    +#+
    0.57
    AutoScaleMode
    0.55
    Ap
    0.53
     Aper
    0.52
     aps
    0.51
     Apri
    0.50
    Activations Density 0.271%

    No Known Activations