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. 14-GEMMASCOPE-RES-16K
    6. 6602
    Prev
    Next
    INDEX
    Explanations

    concepts related to burden and responsibility 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 @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    paedic
    -0.57
     ")");
    -0.57
    aronder
    -0.54
    !*\
    -0.52
    ISupport
    -0.51
    __":
    -0.51
     EconPapers
    -0.51
     ModelExpression
    -0.50
    awtextra
    -0.50
    Datuak
    -0.49
    POSITIVE LOGITS
    cydow
    0.61
     Inscrivez
    0.60
    lead
    0.56
     lead
    0.54
     silenzio
    0.52
    ahead
    0.50
     duquel
    0.50
     équipée
    0.50
     Vordergrund
    0.49
     memimpin
    0.49
    Activations Density 0.320%

    No Known Activations