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-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 10398
    Prev
    Next
    INDEX
    Explanations

    references to various types of bows or bow-related terms

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

    "bow" and associated terms

    np_acts-logits-general · gemini-2.0-flash

    bow and related words

    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
    nsf
    -0.56
    Edm
    -0.54
    FailureListener
    -0.53
    ThroughAttribute
    -0.52
     Haas
    -0.51
    圳
    -0.50
    erus
    -0.49
     hạ
    -0.49
    TimePicker
    -0.49
    ClientSize
    -0.48
    POSITIVE LOGITS
     Bow
    1.53
    Bow
    1.50
     bow
    1.50
     BOW
    1.42
     bows
    1.33
    bow
    1.20
     arrows
    1.14
    BOW
    1.14
     Bowman
    1.12
     arrow
    1.10
    Activations Density 0.147%

    No Known Activations