© 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. 6-GEMMASCOPE-RES-16K
    11. 5682
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and operations related to factors and variables

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

    mathematical instructions and problem-solving steps (like "List", "Show", "Let", "Determine", "Suppose", etc.).

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/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.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NameInMap
    -0.50
    日閲覧
    -0.45
    iser
    -0.45
    ева
    -0.44
    xy
    -0.43
    ides
    -0.43
    扇
    -0.42
      
    -0.42
     ‘
    -0.42
    ised
    -0.42
    POSITIVE LOGITS
    ंदीखरीदारी
    0.89
     صوتيه
    0.82
    forChild
    0.82
    WebControls
    0.77
    DeleteBehavior
    0.72
    etheless
    0.69
     IDisposable
    0.68
    ReusableCell
    0.68
     GenerationType
    0.68
    AutoScale
    0.67
    Activations Density 0.680%

    No Known Activations