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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 10-GEMMASCOPE-RES-16K
    6. 3039
    Prev
    Next
    INDEX
    Explanations

    medical terminology and technical concepts related to algorithms and data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    </s>
    -0.69
    +#+#
    -0.62
     iParam
    -0.62
    WidgetItem
    -0.58
    GeneratedMessage
    -0.56
    CloseOperation
    -0.56
    expandindo
    -0.55
     Beding
    -0.54
    <s>
    -0.54
    jamientos
    -0.54
    POSITIVE LOGITS
    VIAF
    1.44
     VIAF
    1.28
     Vance
    1.17
     Vle
    1.07
    getV
    1.07
    VH
    1.04
     VH
    1.02
     mV
    1.00
     Vaughn
    1.00
     Vane
    1.00
    Activations Density 1.145%

    No Known Activations