© 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 - 65k
    5. 0-GEMMASCOPE-RES-65K
    6. 9822
    Prev
    Next
    INDEX
    Explanations

    references to mirrors and related optical devices

    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
    LookAnd
    -0.71
     Paglinawan
    -0.67
    ByExample
    -0.61
    PYX
    -0.59
    IUrlHelper
    -0.59
    CppMethod
    -0.58
    DebuggerStep
    -0.58
    jspx
    -0.58
     chi̍t
    -0.57
    (!__
    -0.56
    POSITIVE LOGITS
    Mirror
    1.08
     Mirror
    1.06
     mirrors
    1.03
     Mirrors
    1.02
     mirror
    1.02
     mirroring
    0.94
    mirror
    0.92
     MIRROR
    0.91
     mirrored
    0.85
    Mirrors
    0.81
    Activations Density 0.038%

    No Known Activations