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. 11754
    Prev
    Next
    INDEX
    Explanations

    references to coding environments, particularly IDEs and their associated tools or settings

    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
     NgModule
    -0.58
    ArgsConstructor
    -0.56
    ChildScrollView
    -0.54
    RLock
    -0.54
    tagli
    -0.51
    VersionUID
    -0.49
    PostExecute
    -0.48
     cap
    -0.48
    leria
    -0.47
    GraphicsUnit
    -0.47
    POSITIVE LOGITS
    intellij
    0.90
     Muses
    0.69
     VSC
    0.68
    netbeans
    0.68
     IntelliJ
    0.67
    errHandler
    0.66
     tooling
    0.66
     PhpStorm
    0.65
    ſelf
    0.65
     ་་
    0.63
    Activations Density 0.696%

    No Known Activations