© 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. 1709
    Prev
    Next
    INDEX
    Explanations

    references to sharing and sharing-related actions

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

    "share" and its variations

    np_acts-logits-general · gemini-2.0-flash

    sharing and portions

    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
    LookAnd
    -0.68
    Donnie
    -0.64
     فريبيس
    -0.63
    banded
    -0.61
     Donnie
    -0.59
     defaultstate
    -0.56
    maf
    -0.54
     AssemblyProduct
    -0.53
    ttt
    -0.51
    ViewInit
    -0.51
    POSITIVE LOGITS
     shares
    0.94
     SHARE
    0.90
     Shares
    0.89
     Sharing
    0.82
     Share
    0.80
     share
    0.76
    SHARED
    0.75
    Sharing
    0.74
     comparte
    0.74
     comparten
    0.73
    Activations Density 0.138%

    No Known Activations