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. 5225
    Prev
    Next
    INDEX
    Explanations

    conditional statements and function return statements in programming

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

    Code, comparison, or differences in code

    np_acts-logits-general · gemini-2.0-flash

    comparison logic

    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
    ContentAsync
    -1.11
    ьаж
    -0.82
    RegistryLite
    -0.74
    ymce
    -0.72
    canestro
    -0.70
    DoubleQuotes
    -0.70
    
    -0.64
     كومونز
    -0.61
     unknownFields
    -0.61
     Buren
    -0.61
    POSITIVE LOGITS
    getClass
    0.50
     differences
    0.49
    other
    0.47
     other
    0.47
     comparisons
    0.47
     thine
    0.46
     getClass
    0.45
     priesthood
    0.44
     theirs
    0.44
     Vergleich
    0.43
    Activations Density 0.078%

    No Known Activations