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. 3-GEMMASCOPE-RES-16K
    6. 12274
    Prev
    Next
    INDEX
    Explanations

    references to significant changes or turning points in life or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lorette
    -0.53
    >())
    -0.50
    cinfo
    -0.49
    ellido
    -0.49
     recycled
    -0.48
    ukone
    -0.46
     InputDecoration
    -0.46
     Pilate
    -0.46
    vides
    -0.45
    exe
    -0.45
    POSITIVE LOGITS
     breakthrough
    0.93
     change
    0.89
     changé
    0.87
     revolution
    0.86
     breakthroughs
    0.85
    ագրություններ
    0.84
     Breakthrough
    0.83
     changer
    0.82
     transformation
    0.82
     revolu
    0.82
    Activations Density 0.351%

    No Known Activations