© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 9025
    Prev
    Next
    INDEX
    Explanations

    references to arrows and expressions in a technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ChildScrollView
    -0.62
     jScrollPane
    -0.58
    }$​
    -0.57
    ymce
    -0.56
    )_/¯
    -0.55
     arşivlendi
    -0.54
     noDo
    -0.52
     tartalomajánló
    -0.50
    RefNanny
    -0.50
    Measured
    -0.50
    POSITIVE LOGITS
     arrow
    0.82
    Arrow
    0.77
    equation
    0.71
     Arrow
    0.71
     ARROW
    0.66
    arrow
    0.66
    Equation
    0.65
     equation
    0.61
     Equation
    0.61
    ARROW
    0.60
    Activations Density 0.229%

    No Known Activations