© 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-2-2B
    7. Residual Stream - 16k
    9. 14-GEMMASCOPE-RES-16K
    11. 10158
    Prev
    Next
    INDEX
    Explanations

    instances of self-identity or personal reflection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ModelExpression
    -0.66
    rungsseite
    -0.61
    savevideo
    -0.56
    }^{+\
    -0.55
    Tazama
    -0.53
     kasarigan
    -0.52
    osoba
    -0.51
    koff
    -0.51
     âme
    -0.50
    esModule
    -0.50
    POSITIVE LOGITS
     Goodreads
    0.72
     Kindle
    0.57
     SwitchCompat
    0.57
     kindle
    0.56
     characters
    0.53
     turbin
    0.52
    WebControls
    0.51
    AspNetCore
    0.49
     steampunk
    0.48
     AspNetCore
    0.47
    Activations Density 0.226%

    No Known Activations