Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 12366
    Prev
    Next
    INDEX
    Explanations

    the presence of non-standard spacing or characters in the text

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

    Legal or legislative texts

    np_acts-logits-general · gemini-2.0-flash

    legally written or completed texts

    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
     bezeichneter
    -0.74
    DOCTYPE
    -0.72
    SceneManagement
    -0.72
    彡
    -0.70
     Walkover
    -0.69
    clyde
    -0.68
     ostavi
    -0.68
     ويكيميديا
    -0.67
    protoimpl
    -0.67
    addGap
    -0.67
    POSITIVE LOGITS
    <blockquote>
    0.87
    “
    0.71
            
    0.69
     дописавши
    0.64
                            
    0.64
                    
    0.63
     valmis
    0.62
     Escolar
    0.62
     dår
    0.61
             
    0.61
    Activations Density 0.189%

    No Known Activations