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. 20-GEMMASCOPE-RES-65K
    6. 1225
    Prev
    Next
    INDEX
    Explanations

    various themes and their attributes in a technical context

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

    properties related to themes and color settings in programming or design contexts

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

    theme/themes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CodedInputStream
    -0.67
     OMITBAD
    -0.66
     kaynağından
    -0.65
     تضيفلها
    -0.62
    
    
    -0.60
    SerializedSize
    -0.60
    writeFieldEnd
    -0.59
    rophore
    -0.58
     برانيه
    -0.57
    <h6>
    -0.57
    POSITIVE LOGITS
    textTheme
    0.63
     Theme
    0.56
    modes
    0.53
    WireFormat
    0.52
    CompleteListener
    0.51
    ษัท
    0.51
    OGND
    0.49
    (--
    0.49
    options
    0.48
     sessionFactory
    0.48
    Activations Density 0.007%

    No Known Activations