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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 3376
    Prev
    Next
    INDEX
    Explanations

    references to ranges in data or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للاسماء
    -0.84
    $.
    
    -0.77
    ")));
    
    -0.77
    Autoritní
    -0.76
     "..\..\..\
    -0.72
    évaluateur
    -0.69
    MENAFN
    -0.68
     مرئيه
    -0.68
    ()]
    
    -0.68
    '),
    
    -0.67
    POSITIVE LOGITS
    Range
    1.91
     Range
    1.64
    range
    1.58
    RANGE
    1.50
     RANGE
    1.45
    ranges
    1.39
     ranges
    1.22
     Ranges
    1.20
    Ranges
    1.20
     range
    1.09
    Activations Density 0.162%

    No Known Activations