© 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. 6496
    Prev
    Next
    INDEX
    Explanations

    words associated with the concept of "opening" or "accessing."

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

    the word "open"

    np_acts-logits-general · gemini-2.0-flash

    open up, open doors, open minds

    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
     للمعارف
    -0.76
    rungsseite
    -0.71
    TypedDataSet
    -0.62
     unknownFields
    -0.56
     HasFactory
    -0.54
    存于互联网档案馆
    -0.54
    copyWith
    -0.53
    ียญ
    -0.51
     AssemblyCulture
    -0.50
    tanleria
    -0.49
    POSITIVE LOGITS
     opened
    1.29
     Opens
    1.21
     opens
    1.17
    opened
    1.16
     opening
    1.14
     doors
    1.13
    Opened
    1.12
     openings
    1.11
     Opened
    1.10
     open
    1.09
    Activations Density 0.080%

    No Known Activations