© 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 - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 28180
    Prev
    Next
    INDEX
    Explanations

    instances of death and dying

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

    concept of death or dying

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    Composable
    -0.69
     Caval
    -0.65
     للاسماء
    -0.64
    uous
    -0.63
    ligators
    -0.61
     šal
    -0.60
    clat
    -0.60
    ufficio
    -0.59
    useppe
    -0.59
    ="../../
    -0.58
    POSITIVE LOGITS
     mourir
    0.94
    jooq
    0.81
     died
    0.71
     mourut
    0.70
    die
    0.70
     meurt
    0.69
    glEnd
    0.68
    Die
    0.66
    đi
    0.65
     CRY
    0.64
    Activations Density 0.012%

    No Known Activations