© 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. 34-GEMMASCOPE-RES-16K
    11. 13012
    Prev
    Next
    INDEX
    Explanations

    references to personal belongings or significant items in a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    出版年
    -0.56
     protoimpl
    -0.55
    AndEndTag
    -0.51
    Espèce
    -0.50
     lenker
    -0.49
    adpleegd
    -0.46
    InlineData
    -0.46
    UseVisualStyle
    -0.45
    IntoConstraints
    -0.45
    portál
    -0.45
    POSITIVE LOGITS
    🏾
    1.11
     niggas
    0.79
     nigga
    0.72
    🏿
    0.71
     smh
    0.69
     Jamaican
    0.67
     Afro
    0.67
    🏽
    0.66
     African
    0.62
     dope
    0.61
    Activations Density 0.534%

    No Known Activations