Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 9032
    Prev
    Next
    INDEX
    Explanations

    connections and realizations that improve understanding of a topic

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

    "Now that I think" or "Edit:" phrases

    np_acts-logits-general · gemini-2.0-flash

    think of it

    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
    MigrationBuilder
    -0.52
    ọi
    -0.44
     mudah
    -0.39
     Initialized
    -0.38
    幸いです
    -0.38
     ơn
    -0.37
     vol
    -0.37
     frustrating
    -0.36
     µ
    -0.35
    reactstrap
    -0.35
    POSITIVE LOGITS
    rungsseite
    1.01
     realization
    0.98
     realisation
    0.97
     realising
    0.95
     realizing
    0.93
     realised
    0.91
     thought
    0.89
     realized
    0.89
     noticing
    0.87
    thought
    0.85
    Activations Density 0.226%

    No Known Activations