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. 6-GEMMASCOPE-RES-16K
    6. 12279
    Prev
    Next
    INDEX
    Explanations

    references to JavaScript and CSS frameworks or libraries being used

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hyrchwyd
    -0.53
     postale
    -0.46
    :+:
    -0.44
    нциклопедия
    -0.42
    はじめに
    -0.41
     Aris
    -0.41
    ↵
    -0.41
    flink
    -0.41
    mmä
    -0.40
     filma
    -0.40
    POSITIVE LOGITS
     архивлан
    0.85
    +#+#
    0.79
     AssemblyProduct
    0.79
     <=",
    0.72
    RunAsync
    0.71
    =$?
    0.71
     Daß
    0.69
    Tikang
    0.68
     {:.
    0.67
     wireType
    0.67
    Activations Density 0.141%

    No Known Activations