© 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. 4-GEMMASCOPE-RES-16K
    11. 10325
    Prev
    Next
    INDEX
    Explanations

    references to personal identity and expressions of self-perception

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    بوابة
    -0.71
    BoxShadow
    -0.63
     Laughter
    -0.61
    apimachinery
    -0.60
    inação
    -0.56
     PhpStorm
    -0.56
     voedsel
    -0.56
    SaveChangesAsync
    -0.56
    原始内容存档于
    -0.55
     PeEnEo
    -0.55
    POSITIVE LOGITS
    tvguidetime
    0.47
    <!--
    0.46
    sigh
    0.45
    öszi
    0.45
    SequentialGroup
    0.45
    Cleared
    0.45
    Tas
    0.45
    jock
    0.44
    ()]
    0.44
    Cyfeiriadau
    0.44
    Activations Density 0.413%

    No Known Activations