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. 7909
    Prev
    Next
    INDEX
    Explanations

    code-related syntactic patterns and structures

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

    Tokens after equals signs or returns

    np_acts-logits-general · gemini-2.0-flash

    new content or resource assignment

    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
    =[]
    -0.60
     ushort
    -0.58
     atof
    -0.58
    clearTimeout
    -0.57
     CGRect
    -0.56
     atoi
    -0.54
     hwnd
    -0.54
     CGFloat
    -0.51
     parseFloat
    -0.51
    =['
    -0.50
    POSITIVE LOGITS
     new
    1.00
    new
    1.00
    null
    0.87
     null
    0.81
     ModelExpression
    0.74
    })));
    0.70
     Collections
    0.70
     Arrays
    0.69
    )));
    0.68
     !"
    0.67
    Activations Density 0.138%

    No Known Activations