© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 27-GEMMASCOPE-RES-16K
    11. 9859
    Prev
    Next
    INDEX
    Explanations

    technical terms and code-related phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الرياضيه
    -0.80
    aarrggbb
    -0.77
    AndEndTag
    -0.77
    StructEnd
    -0.72
    RTLR
    -0.72
    OGND
    -0.69
     betweenstory
    -0.69
     Infórmanos
    -0.69
    دانشنامهٔ
    -0.68
    __*/
    -0.67
    POSITIVE LOGITS
     there
    0.90
     we
    0.81
     it
    0.79
     they
    0.73
    there
    0.60
    ,
    0.58
     you
    0.56
     he
    0.52
    they
    0.44
    you
    0.44
    Activations Density 0.690%

    No Known Activations