© 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. 21-GEMMASCOPE-RES-16K
    6. 14140
    Prev
    Next
    INDEX
    Explanations

    programming syntax and structure related to shaders and JSON data formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GraphicsUnit
    -0.97
    addPreferredGap
    -0.96
    DeleteBehavior
    -0.95
     GenerationType
    -0.89
    HasForeignKey
    -0.88
     autorytatywna
    -0.88
    $.
    
    -0.88
    PostExecute
    -0.87
     $_"
    -0.87
     disambiguazione
    -0.87
    POSITIVE LOGITS
    ↵
    0.75
     """
    0.72
    """
    0.66
     "
    0.58
     '''
    0.57
    '''
    0.57
      
    0.52
    <blockquote>
    0.51
     "\
    0.50
    "\
    0.50
    Activations Density 0.200%

    No Known Activations