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. 15-GEMMASCOPE-RES-16K
    6. 2808
    Prev
    Next
    INDEX
    Explanations

    specific technical terms and references related to scientific methods, laws, or the judicial system

    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
    DropColumn
    -0.46
    Dom
    -0.43
     Dux
    -0.43
    Einzelnachweise
    -0.41
    ########.
    -0.40
    StructEnd
    -0.39
    ab
    -0.39
     Astral
    -0.39
     przer
    -0.39
    Mo
    -0.39
    POSITIVE LOGITS
     biais
    0.91
    tagHelperRunner
    0.77
    pulumi
    0.73
    LookAnd
    0.71
    tagHelper
    0.69
     resourceCulture
    0.69
    ValueStyle
    0.68
    UserScript
    0.68
    PyExc
    0.67
     Paglinawan
    0.66
    Activations Density 0.637%

    No Known Activations