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. 13-GEMMASCOPE-RES-16K
    6. 6757
    Prev
    Next
    INDEX
    Explanations

    terms related to programming constructs, particularly those involving data handling and manipulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    references to technical constructs or components in code, particularly those related to data processing or manipulation

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    TagMode
    -0.74
    AppMethodBeat
    -0.51
    foglal
    -0.49
    parsedMessage
    -0.47
    DebuggerNonUser
    -0.47
     Broder
    -0.46
    OuterClass
    -0.45
    AddField
    -0.45
    Now
    -0.44
     terecht
    -0.44
    POSITIVE LOGITS
    RTSC
    0.62
    provider
    0.62
     provider
    0.61
     personalizado
    0.61
    Sqft
    0.58
    Sucesor
    0.58
     Provider
    0.57
    出版年
    0.57
     providers
    0.57
    Provider
    0.57
    Activations Density 0.664%

    No Known Activations