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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 1766
    Prev
    Next
    INDEX
    Explanations

    terms related to pharmacological mechanisms and biological responses

    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
     SimpleName
    -0.55
    pushFollow
    -0.55
    PathVariable
    -0.55
    öng
    -0.52
    TextWatcher
    -0.51
    凡
    -0.50
     setuptools
    -0.49
    WindowConstants
    -0.49
    kowych
    -0.48
     far
    -0.48
    POSITIVE LOGITS
    ReusableCell
    0.72
    ódz
    0.64
    WritableDatabase
    0.63
     <=",
    0.62
     يتيمه
    0.62
    Carriera
    0.60
     snippetHide
    0.59
    matchCondition
    0.59
    }],
    0.59
    PhysRev
    0.58
    Activations Density 2.225%

    No Known Activations