© 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. 18-GEMMASCOPE-RES-16K
    11. 4064
    Prev
    Next
    INDEX
    Explanations

    references to characters and roles in a narrative or story context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "of" followed by "the."

    np_acts-logits-general · gemini-2.0-flash

    of the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     itſelf
    -0.72
    PYX
    -0.68
    DockStyle
    -0.63
    RegressionTest
    -0.58
    AnimationsModule
    -0.57
     Baillargeon
    -0.57
    ioutil
    -0.56
     themſelves
    -0.56
    ſelves
    -0.55
    unknownFields
    -0.54
    POSITIVE LOGITS
     whom
    0.79
     فريبيس
    0.65
    otoro
    0.58
    whom
    0.56
     turno
    0.55
     who
    0.52
    brandt
    0.52
    enski
    0.46
    AutoScale
    0.46
    carbonyl
    0.45
    Activations Density 0.208%

    No Known Activations