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 - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 52959
    Prev
    Next
    INDEX
    Explanations

    references to specific data or structured information related to studies or articles

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

    doi links and references

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    setVerticalGroup
    -0.65
    ⓧ
    -0.53
    rrggbb
    -0.53
     CreateTagHelper
    -0.52
    SharedDtor
    -0.51
     diamants
    -0.51
    silueta
    -0.49
     étranger
    -0.48
     Waterhouse
    -0.47
    bootstrapcdn
    -0.47
    POSITIVE LOGITS
    AutoField
    0.65
     незавершена
    0.59
    odeon
    0.56
     ExecuteAsync
    0.56
    badlogic
    0.53
    WindowConstants
    0.52
    Portail
    0.50
    bewerken
    0.50
    __":
    
    0.49
    :])
    0.48
    Activations Density 0.032%

    No Known Activations