© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 12482
    Prev
    Next
    INDEX
    Explanations

    phrases related to achievement and accountability

    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
     Diſ
    -0.56
    ￡
    -0.56
    parsedMessage
    -0.56
     fubject
    -0.51
     pleaſure
    -0.51
     withdrawal
    -0.50
    calar
    -0.50
    BeginContext
    -0.49
     rút
    -0.49
     <<<<<<<<<<<<<<
    -0.46
    POSITIVE LOGITS
     needed
    0.86
     required
    0.81
     necessary
    0.79
     desired
    0.72
     nécessaires
    0.72
    required
    0.71
    needed
    0.71
     necessari
    0.70
     nécessaire
    0.68
     expected
    0.67
    Activations Density 0.299%

    No Known Activations