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. 3-GEMMASCOPE-RES-16K
    6. 8280
    Prev
    Next
    INDEX
    Explanations

    references to digital object identifiers (DOIs) and URLs for academic papers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    okhttp
    -0.50
    gpl
    -0.50
    picasso
    -0.49
     vernac
    -0.45
     imp
    -0.44
    WebpackPlugin
    -0.44
    enfone
    -0.44
    withOpacity
    -0.43
    ulp
    -0.43
    ppie
    -0.43
    POSITIVE LOGITS
     Roskov
    0.81
    MigrationBuilder
    0.81
     bezeichneter
    0.79
     thyself
    0.74
     papyrus
    0.72
     Theſe
    0.70
     transfieras
    0.68
    Портали
    0.67
    :✨
    0.67
    basicConfig
    0.66
    Activations Density 0.356%

    No Known Activations