© 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. 4-GEMMASCOPE-RES-16K
    11. 11605
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and terms related to algebraic operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     дописавши
    -0.98
    principalTable
    -0.95
    expandindo
    -0.93
     للاسماء
    -0.92
    @[+][
    -0.90
     <<<<<<<<<<<<<<
    -0.86
    AccessorTable
    -0.83
    extendable
    -0.80
    (!__
    -0.78
     endblock
    -0.76
    POSITIVE LOGITS
     
    0.55
     North
    0.53
    Affirmed
    0.49
    0.48
     H
    0.48
    //{

    0.47
    -
    0.46
     "
    0.46
     ThemeData
    0.46
     is
    0.45
    Activations Density 1.826%
    No Known Activations