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. 2-GEMMASCOPE-RES-16K
    6. 6850
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "rough" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     useState
    -0.71
    Filmographie
    -0.69
    useState
    -0.66
    baomidou
    -0.64
     jspb
    -0.60
    ButterKnife
    -0.60
     تعدى
    -0.58
     Pavlov
    -0.58
    ExtendWith
    -0.58
    퀀
    -0.57
    POSITIVE LOGITS
     rough
    3.56
     Rough
    3.21
    Rough
    3.02
    rough
    2.98
    ROUGH
    2.16
     roughness
    1.72
    ghest
    1.54
     kasar
    1.36
     rou
    1.33
     ruff
    1.33
    Activations Density 0.062%

    No Known Activations