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. 16-GEMMASCOPE-RES-16K
    6. 187
    Prev
    Next
    INDEX
    Explanations

    information related to statistical growth and increases over time

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

    Prepositions and percentages

    np_acts-logits-general · gemini-2.0-flash

    per hour/month/year

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     extended
    -0.45
    mpar
    -0.43
    ToJson
    -0.41
    ılmış
    -0.40
     Extended
    -0.40
    AnchorStyles
    -0.39
    vatar
    -0.38
    span
    -0.37
     Mell
    -0.37
     bade
    -0.35
    POSITIVE LOGITS
     daily
    0.97
    MigrationBuilder
    0.91
    daily
    0.89
    Tikang
    0.86
     continuamente
    0.86
     hourly
    0.84
     yearly
    0.83
     annually
    0.83
     continuously
    0.82
     constantemente
    0.82
    Activations Density 0.305%

    No Known Activations