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. 20-GEMMASCOPE-RES-16K
    6. 15308
    Prev
    Next
    INDEX
    Explanations

    references to technical specifications and programming concepts

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

    after "DLT_" or "GO:" in large hexadecimal numbers

    np_acts-logits-general · gemini-2.0-flash

    biological and technical processes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
                                   
    -1.25
    …………………………………………
    -1.09
    									
    -1.05
    GEBURTSDATUM
    -1.01
    										
    -1.01
    								
    -1.00
    															
    -0.98
    											
    -0.97
    													
    -0.97
    																
    -0.97
    POSITIVE LOGITS
    著
    0.47
    migrationBuilder
    0.45
     ...
    0.45
    nonatomic
    0.43
    ℗
    0.42
    ....
    0.42
     ..
    0.41
    afterEach
    0.41
    ..
    0.41
    lepaskan
    0.40
    Activations Density 0.367%

    No Known Activations