© 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. 15-GEMMASCOPE-RES-16K
    11. 2617
    Prev
    Next
    INDEX
    Explanations

    references to API endpoints and documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PreferredItem
    -0.84
    ViewFeatures
    -0.61
    tagHelperRunner
    -0.59
    idopsis
    -0.58
    AndEndTag
    -0.57
    ptonshire
    -0.57
    
    -0.57
     ujednoznacz
    -0.57
    rizona
    -0.56
     bershka
    -0.55
    POSITIVE LOGITS
     springfox
    0.69
    Swagger
    0.68
     noqa
    0.63
     findViewById
    0.62
    OGRAPH
    0.60
    glBind
    0.55
    তথ্যসূত্র
    0.54
    føl
    0.54
    ApiModelProperty
    0.54
     rense
    0.53
    Activations Density 0.019%

    No Known Activations