© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 11502
    Prev
    Next
    INDEX
    Explanations

    references to familial and interpersonal relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    preceding auxiliary verbs

    np_acts-logits-general · gemini-2.0-flash

    possession and consequence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/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.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     виправивши
    -0.66
     nonUne
    -0.61
     AppCompatTheme
    -0.59
    Obrázky
    -0.58
     Normdatei
    -0.57
     nakalista
    -0.56
    ParallelGroup
    -0.56
     ModelRenderer
    -0.55
    amssymb
    -0.54
    httphttps
    -0.54
    POSITIVE LOGITS
    ArgsConstructor
    0.36
     posses
    0.35
     had
    0.34
     exert
    0.33
     possessed
    0.32
     exer
    0.32
     ejer
    0.32
     erlang
    0.32
     exerted
    0.32
     gained
    0.31
    Activations Density 0.530%

    No Known Activations