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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 12891
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "be."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 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
     autorytatywna
    -0.68
     Chwiliwch
    -0.68
    ientras
    -0.61
    -------
    -0.60
    Tikang
    -0.57
    новниш
    -0.56
    principalColumn
    -0.55
    SourceChecksum
    -0.54
    ValueStyle
    -0.53
     &___
    -0.51
    POSITIVE LOGITS
     being
    0.77
     Being
    0.72
    Being
    0.68
    ToBe
    0.65
    being
    0.63
     BEING
    0.57
     becoming
    0.48
     became
    0.47
     להיות
    0.45
     Becoming
    0.44
    Activations Density 0.154%

    No Known Activations