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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-GEMMASCOPE-RES-16K
    6. 6895
    Prev
    Next
    INDEX
    Explanations

    elements related to data fetching and processing in code, particularly in conjunction with promise handling and file reading

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tartalomajánló
    -0.77
    Gweler
    -0.64
    setupUi
    -0.58
     Sodom
    -0.58
    ścic
    -0.58
     للمعارف
    -0.55
    MessageOf
    -0.55
    NewUrlParser
    -0.54
    webElementGuid
    -0.54
    orative
    -0.54
    POSITIVE LOGITS
    DataSnapshot
    0.54
     dataSnapshot
    0.53
    itza
    0.52
     ComVisible
    0.50
     transférez
    0.49
    relative
    0.47
    hips
    0.47
     relative
    0.47
    utilisons
    0.47
     ospiti
    0.46
    Activations Density 0.078%

    No Known Activations