© 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. 33-GEMMASCOPE-RES-16K
    11. 14147
    Prev
    Next
    INDEX
    Explanations

    quantitative data and statistics related to population and demographics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    万美元
    -0.53
    億円
    -0.44
     Pare
    -0.40
     Figure
    -0.40
    万円
    -0.40
     Par
    -0.39
    ğraf
    -0.39
    انجليز
    -0.36
    万元
    -0.36
     Roland
    -0.36
    POSITIVE LOGITS
     thousands
    0.81
    thousands
    0.75
    Thousands
    0.69
     ribuan
    0.68
     hundreds
    0.68
     Thousands
    0.66
     milliers
    0.63
    Hundreds
    0.59
    hundreds
    0.59
     milhares
    0.58
    Activations Density 0.213%

    No Known Activations