© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 0-GEMMASCOPE-RES-65K
    11. 9923
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of "futures" and "infinite" structures or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Administrativna
    -1.11
     consultato
    -0.92
    PerformLayout
    -0.85
     AttributeSet
    -0.79
    JspWriter
    -0.77
    DockStyle
    -0.77
    endphp
    -0.77
     percolation
    -0.76
     mijne
    -0.75
    WebServlet
    -0.75
    POSITIVE LOGITS
     futures
    0.69
     POS
    0.66
     Futures
    0.63
    POS
    0.60
     primary
    0.58
     Proven
    0.57
    ancing
    0.50
    cin
    0.50
    (/\
    0.50
     المعيارى
    0.50
    Activations Density 0.048%

    No Known Activations