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. 8-GEMMASCOPE-RES-16K
    6. 15171
    Prev
    Next
    INDEX
    Explanations

    programming-related annotations and framework elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ISupport
    -0.56
     Redskins
    -0.50
    ver
    -0.49
     afo
    -0.49
    HtmlAttribute
    -0.48
    poz
    -0.47
    mtrl
    -0.46
     Swa
    -0.46
     SDLK
    -0.45
     nữa
    -0.44
    POSITIVE LOGITS
     defaultstate
    1.48
    localctx
    1.42
     TestBed
    1.36
    MigrationBuilder
    1.33
     BrowserModule
    1.23
    ConstraintMaker
    1.19
    SpringBootTest
    1.16
     onCreateView
    1.14
     EconPapers
    1.07
    adaptiveStyles
    1.05
    Activations Density 0.015%

    No Known Activations