Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 3491
    Prev
    Next
    INDEX
    Explanations

    various forms and references to attributes in a programming or markup context

    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
    بوابة
    -1.03
     snippetHide
    -0.99
    SourceChecksum
    -0.87
    RTLU
    -0.85
    parsedMessage
    -0.85
     /\.(
    -0.85
    Rujuakan
    -0.83
     Michaelis
    -0.82
    contentLoaded
    -0.81
    oredCriteria
    -0.80
    POSITIVE LOGITS
     attributes
    2.28
     attribute
    2.21
    attributes
    2.06
     Attributes
    1.96
     Attribute
    1.93
    Attributes
    1.90
    attribute
    1.82
    Attribute
    1.72
     attribut
    1.57
    Attr
    1.50
    Activations Density 0.077%

    No Known Activations