© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 6431
    Prev
    Next
    INDEX
    Explanations

    references to the Eclipse software and its associated plugins or licenses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    帖最后由
    -0.76
    fromCharCode
    -0.74
    complexType
    -0.73
    routeProvider
    -0.72
    omitempty
    -0.72
    AccessFile
    -0.70
     Normdatei
    -0.69
    fortawesome
    -0.69
     @"/
    -0.67
    @[+][
    -0.66
    POSITIVE LOGITS
    eclipse
    2.73
     Eclipse
    1.36
     eclipse
    1.33
    Eclipse
    1.28
    jface
    1.02
     eclips
    0.76
    lipse
    0.69
     SWT
    0.67
    vscode
    0.67
    Erreferentziak
    0.65
    Activations Density 0.027%

    No Known Activations