© 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-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 15915
    Prev
    Next
    INDEX
    Explanations

    occurrences of the pronoun "I" along with related personal expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    き
    -0.51
    choc
    -0.49
    REMARKS
    -0.49
    PHPExcel
    -0.47
    lippe
    -0.47
     muelle
    -0.45
    ús
    -0.44
    onne
    -0.44
     Paix
    -0.44
     alug
    -0.44
    POSITIVE LOGITS
     MainAxisSize
    0.78
     TextInputType
    0.77
     snippetHide
    0.75
     विश्वसनीयता
    0.72
     صوتيه
    0.71
    zegor
    0.70
     sumpay
    0.69
    tagHelperRunner
    0.69
    saraba
    0.69
    ()")
    0.69
    Activations Density 0.189%

    No Known Activations