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. 22-GEMMASCOPE-RES-16K
    6. 3325
    Prev
    Next
    INDEX
    Explanations

    sections and formatting elements typically found in academic papers

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

    Text segment headings

    np_acts-logits-general · gemini-2.0-flash

    document section headers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    %;
    
    -0.55
    %">
    -0.54
    glGen
    -0.50
    '],
    
    -0.50
    ednesdays
    -0.48
    <bos>
    -0.47
    =#{
    -0.47
    '''
    
    -0.47
    fera
    -0.47
    %',
    -0.47
    POSITIVE LOGITS
     متعلقه
    1.25
    rungsseite
    0.91
    ंदीखरीदारी
    0.85
    MessageOf
    0.79
    parsedMessage
    0.79
    :✨
    0.73
    ValueStyle
    0.73
     kasarigan
    0.72
    הערות
    0.72
     مشين
    0.71
    Activations Density 0.470%

    No Known Activations