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. 5-GEMMASCOPE-RES-16K
    6. 1108
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "life" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     aveug
    -0.65
    ManyToOne
    -0.58
     habido
    -0.57
    PullParser
    -0.54
    bewerken
    -0.53
     تانيه
    -0.52
     trecut
    -0.51
    difice
    -0.51
     Melt
    -0.50
     caballeros
    -0.50
    POSITIVE LOGITS
     life
    2.04
     Life
    1.86
    life
    1.82
     LIFE
    1.77
    Life
    1.74
    LIFE
    1.65
     lifes
    1.54
     lives
    1.48
     Leben
    1.39
    lifes
    1.37
    Activations Density 0.168%

    No Known Activations