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. 10-GEMMASCOPE-RES-16K
    6. 15642
    Prev
    Next
    INDEX
    Explanations

    mentions of funerals and related contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     виправивши
    -0.88
    AccessorTable
    -0.84
    IsMutable
    -0.82
    jména
    -0.74
     unknownFields
    -0.73
     signUp
    -0.72
    DIPSETTING
    -0.72
     Kitts
    -0.72
     rowspan
    -0.71
     Bretaña
    -0.71
    POSITIVE LOGITS
     funeral
    1.37
     Funeral
    1.33
    Funeral
    1.22
     FUNERAL
    1.15
    funeral
    1.15
     funerals
    1.05
    erals
    1.01
     underta
    0.77
     funer
    0.76
     Coffin
    0.69
    Activations Density 0.062%

    No Known Activations