© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 845
    Prev
    Next
    INDEX
    Explanations

    details regarding memorial services and funerals

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

    before "funeral" or "trial"

    np_acts-logits-general · gemini-2.0-flash

    funeral

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    帖最后由
    -0.61
     pinulongan
    -0.59
    liceerd
    -0.55
    cetos
    -0.54
     CURIAM
    -0.53
    compar
    -0.53
    下载附件
    -0.53
    CodeAnalysis
    -0.53
     compla
    -0.52
    চ্
    -0.52
    POSITIVE LOGITS
     funeral
    1.27
     Funeral
    1.15
    Funeral
    0.97
     funerals
    0.90
     FUNERAL
    0.90
    funeral
    0.89
    erals
    0.78
     memorial
    0.74
     Celebration
    0.72
     cerimonia
    0.67
    Activations Density 0.105%

    No Known Activations