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. 15-GEMMASCOPE-RES-16K
    6. 2405
    Prev
    Next
    INDEX
    Explanations

    quantitative data or statistics related to percentages and numerical values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ]--;
    -0.76
    ->___
    -0.70
    ']))
    
    -0.65
    ]++;
    -0.64
    >[]
    -0.63
     Meksiku
    -0.61
    ')}}">
    -0.59
    ))))))))
    -0.55
    LinkId
    -0.55
    '])){
    
    -0.54
    POSITIVE LOGITS
    bootstrapcdn
    0.86
    GOTREF
    0.76
     مشين
    0.72
     CreateTagHelper
    0.72
     nakalista
    0.70
    Hentet
    0.69
    ModelAdmin
    0.68
    makeConstraints
    0.65
    AddTagHelper
    0.64
    存于互联网档案馆
    0.59
    Activations Density 0.380%

    No Known Activations