© 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. 15-GEMMASCOPE-RES-16K
    6. 6211
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals, particularly focusing on pronouns and possessive forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Noch
    -0.56
     inva
    -0.54
     Silly
    -0.51
     topp
    -0.50
     comod
    -0.50
     dima
    -0.49
     aspec
    -0.49
     similar
    -0.48
    ctive
    -0.48
     aig
    -0.47
    POSITIVE LOGITS
     himself
    1.59
    himself
    1.42
     Himself
    1.25
     he
    1.20
     she
    1.14
    she
    1.13
     his
    1.12
    hehe
    1.12
    He
    1.10
    úrese
    1.09
    Activations Density 0.362%

    No Known Activations