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. 1-GEMMASCOPE-RES-16K
    6. 13249
    Prev
    Next
    INDEX
    Explanations

    the word "four" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    frameCount
    -0.55
     свиде
    -0.54
     “
    -0.54
     cajas
    -0.53
    ;#
    -0.53
     ​​
    -0.52
    BuildContext
    -0.52
     dis
    -0.51
    ensis
    -0.51
    ondissement
    -0.48
    POSITIVE LOGITS
    Four
    1.08
     Four
    0.99
     Jefus
    0.97
    four
    0.92
     Efq
    0.89
    FOUR
    0.88
     Chriftian
    0.88
     FOUR
    0.85
     quad
    0.83
     Monfieur
    0.82
    Activations Density 0.126%

    No Known Activations