Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 14796
    Prev
    Next
    INDEX
    Explanations

    references to tragic refugee experiences and casualties

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

    Survival, rescue, or migration attempts

    np_acts-logits-general · gemini-2.0-flash

    perilous journeys and survival

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ModelExpression
    -0.72
    contentLoaded
    -0.62
     дописавши
    -0.59
    errHandler
    -0.58
    ReusableCell
    -0.56
     <>",
    -0.56
     onBind
    -0.56
    delwed
    -0.55
     JpaRepository
    -0.53
    BaseActivity
    -0.53
    POSITIVE LOGITS
     survivors
    0.88
     survivor
    0.84
    Survivors
    0.80
     migrants
    0.78
     rescue
    0.77
     Survivors
    0.77
     Rescue
    0.72
    survi
    0.71
     survival
    0.71
    survival
    0.70
    Activations Density 0.129%

    No Known Activations