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. 15737
    Prev
    Next
    INDEX
    Explanations

    phrases related to structure and functionality in programming

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

    preceding "like"

    np_acts-logits-general · gemini-2.0-flash

    following

    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
    ftagPool
    -0.89
    )");
    
    -0.77
    =?,
    -0.76
    .";
    
    -0.75
     lenker
    -0.74
    }.
    
    -0.71
      
    -0.71
     betweenstory
    -0.69
    ArrowToggle
    -0.69
    OGND
    -0.67
    POSITIVE LOGITS
     following
    2.73
    following
    2.40
     folgende
    2.14
     Following
    2.05
    以下
    2.04
     berikut
    2.03
     siguientes
    2.03
     siguiente
    2.01
     følgende
    1.97
    Following
    1.97
    Activations Density 1.116%

    No Known Activations