© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 13279
    Prev
    Next
    INDEX
    Explanations

    words that convey excessiveness or repetition

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

    "Too," "either," "well," "again"

    np_acts-logits-general · gemini-2.0-flash

    additionally

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    ArrowToggle
    -0.51
    ]").
    -0.51
    ''',
    -0.50
    fortawesome
    -0.49
    _"+
    -0.49
    errHandler
    -0.49
    =’
    -0.47
     regola
    -0.47
     می‌تواند
    -0.47
    ('');
    -0.46
    POSITIVE LOGITS
     تانيه
    1.11
    verwijspagina
    0.95
    脚注の使い方
    0.92
     المعيارى
    0.88
     nakalista
    0.80
     disambiguazione
    0.79
     препратки
    0.75
    TOO
    0.74
    
    0.74
    AutoScaleMode
    0.74
    Activations Density 0.194%

    No Known Activations