Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 14-GEMMASCOPE-RES-16K
    6. 4105
    Prev
    Next
    INDEX
    Explanations

    references to innocence and the unjust treatment of individuals, particularly in the context of racial or social issues

    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
    въ
    -0.50
    lığ
    -0.49
     failure
    -0.49
    nebago
    -0.49
     Monfieur
    -0.48
     Spitze
    -0.48
     بث
    -0.48
    丫头
    -0.47
    luste
    -0.46
    PropertyChanging
    -0.46
    POSITIVE LOGITS
    innocent
    0.86
     innocent
    0.85
     inocente
    0.80
    innoc
    0.77
     Innocent
    0.69
     Innoc
    0.65
     MainAxisSize
    0.64
    :✨
    0.64
     utafitiHapana
    0.62
     innocently
    0.62
    Activations Density 0.262%

    No Known Activations