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. 451
    Prev
    Next
    INDEX
    Explanations

    references to biological mechanisms and structures related to phenotypic and genetic traits

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

    preceding "function" or "functional"

    np_acts-logits-general · gemini-2.0-flash

    form and function

    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
    TestingModule
    -0.67
     виправивши
    -0.64
    principalColumn
    -0.64
     Lightboxes
    -0.63
    RefNanny
    -0.62
    UserScript
    -0.62
    expandindo
    -0.58
     TextAppearance
    -0.58
    SourceChecksum
    -0.58
     AttributeSet
    -0.57
    POSITIVE LOGITS
     functional
    0.98
     function
    0.86
     functionally
    0.82
    functional
    0.81
     functionality
    0.79
    function
    0.77
     funcional
    0.75
     Functional
    0.74
     fonction
    0.72
    Functional
    0.72
    Activations Density 0.750%

    No Known Activations