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. 5-GEMMASCOPE-RES-16K
    6. 4457
    Prev
    Next
    INDEX
    Explanations

    references to JavaScript code and related events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     EconPapers
    -0.54
     "/";
    -0.49
    ⓧ
    -0.48
    multer
    -0.47
    Picked
    -0.45
    NameInMap
    -0.45
    Tweets
    -0.45
    الن
    -0.45
    NullException
    -0.44
    UnknownFields
    -0.44
    POSITIVE LOGITS
    PageRoute
    0.81
    UrlResolution
    0.75
    __':
    0.74
    javascript
    0.72
    __':
    
    0.71
    __":
    
    0.66
     InputDecoration
    0.65
    SceneManagement
    0.64
    TargetException
    0.64
    StoryboardSegue
    0.64
    Activations Density 0.164%

    No Known Activations