© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 11738
    Prev
    Next
    INDEX
    Explanations

    variations of the word "pass" in different contexts

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

    "pass" and its variations

    np_acts-logits-general · gemini-2.0-flash

    pass away or pass down

    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
    Luong
    -0.39
    伽
    -0.39
     dispuestos
    -0.39
    Connector
    -0.38
    gam
    -0.37
     klo
    -0.37
     çıktı
    -0.37
    Shall
    -0.37
    Theo
    -0.37
    and
    -0.37
    POSITIVE LOGITS
     Passes
    1.33
     passes
    1.28
     PASS
    1.21
     Pass
    1.20
    passes
    1.18
     pass
    1.18
     Passing
    1.18
     Passed
    1.16
     passed
    1.15
    Passing
    1.15
    Activations Density 0.070%

    No Known Activations