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. 10-GEMMASCOPE-RES-16K
    6. 15853
    Prev
    Next
    INDEX
    Explanations

    phrases indicating problems predominantly caused by human actions or behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ſeveral
    -0.79
     becauſe
    -0.79
     anſ
    -0.76
     Monfieur
    -0.75
     juſt
    -0.72
     theſe
    -0.71
     laſt
    -0.70
     myſelf
    -0.70
     ſtand
    -0.70
     themſelves
    -0.70
    POSITIVE LOGITS
    CloseOperation
    0.79
    windowFixed
    0.69
    GEBURTSDATUM
    0.66
     ExecuteAsync
    0.59
    SPJ
    0.58
     already
    0.57
     AspNetCore
    0.56
    complexContent
    0.56
    >{@
    0.56
     arguably
    0.56
    Activations Density 0.528%

    No Known Activations