© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 1884
    Prev
    Next
    INDEX
    Explanations

    names of places and people

    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
     disambiguazione
    -0.77
     Unger
    -0.73
    oOo
    -0.72
    OrNil
    -0.69
    eriksaan
    -0.68
     EconPapers
    -0.66
     absorb
    -0.65
     Viitattu
    -0.65
     Lacey
    -0.64
    ContentLoaded
    -0.64
    POSITIVE LOGITS
     Newton
    0.77
    Newton
    0.77
     Syd
    0.73
     Nuk
    0.72
     Gwyn
    0.69
    ########.
    0.68
     onCreateView
    0.67
    Syd
    0.66
    dart
    0.66
     Xavi
    0.65
    Activations Density 0.576%

    No Known Activations