© 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 - 65k
    9. 13-GEMMASCOPE-RES-65K
    11. 16657
    Prev
    Next
    INDEX
    Explanations

    terms related to unknown fields in a data structure or protocol

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     NSCoder
    -0.86
     BoxFit
    -0.79
    principalColumn
    -0.79
    MessageTagHelper
    -0.75
    HasForeignKey
    -0.69
    AndroidJUnit
    -0.67
    jacks
    -0.67
     Monfieur
    -0.65
    andExpect
    -0.65
    LookAnd
    -0.62
    POSITIVE LOGITS
    PROTOBUF
    1.63
    NAMESPACE
    1.10
    Hochspringen
    0.89
    Skocz
    0.77
    racite
    0.66
    ]>=
    0.62
    ':[
    0.61
    ;',
    0.60
     unknownFields
    0.60
    ithub
    0.59
    Activations Density 0.004%

    No Known Activations