© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 4783
    Prev
    Next
    INDEX
    Explanations

    dates and references to specific days or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     secundario
    -0.42
     PRIVATE
    -0.39
     funcionario
    -0.37
    :///
    -0.37
    litten
    -0.36
     lusso
    -0.36
    marginVertical
    -0.36
    Demografie
    -0.36
    petto
    -0.35
     secundarios
    -0.35
    POSITIVE LOGITS
    April
    1.01
     April
    0.99
     May
    0.89
    april
    0.84
     april
    0.83
    May
    0.82
    APRIL
    0.81
     spring
    0.78
    spring
    0.78
     APRIL
    0.77
    Activations Density 0.303%

    No Known Activations