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

    Neuronpedia

    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. 4-GEMMASCOPE-RES-16K
    11. 1411
    Prev
    Next
    INDEX
    Explanations

    terms related to biochemistry and medical research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Meksiku
    -0.58
    +:+
    -0.56
    sertation
    -0.56
    paksa
    -0.53
    DebuggerStep
    -0.52
    oflavin
    -0.52
     Executive
    -0.51
    زه
    -0.51
     executive
    -0.51
    upuesto
    -0.50
    POSITIVE LOGITS
    ագրություններ
    0.65
    KEYCODE
    0.63
     estekak
    0.60
    erover
    0.58
    참고
    0.58
    رشف
    0.56
    bukkit
    0.56
    دانشنامهٔ
    0.56
    تقاوى
    0.54
    ANTLR
    0.54
    Activations Density 2.509%

    No Known Activations