© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 3980
    Prev
    Next
    INDEX
    Explanations

    technical terms and jargon related to scientific fields, particularly in biochemistry and molecular biology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     SFR
    -0.72
     judiciaire
    -0.69
    ThemeOverlay
    -0.65
     remonter
    -0.65
     hyal
    -0.64
     judicia
    -0.64
     Perse
    -0.63
     proportionality
    -0.62
     judiciales
    -0.60
     bristle
    -0.58
    POSITIVE LOGITS
    AutoScaleMode
    0.68
    sertation
    0.54
    moires
    0.53
    IActionResult
    0.51
     py
    0.50
     onCreateView
    0.49
    dbo
    0.49
     diary
    0.47
    zeug
    0.47
     års
    0.47
    Activations Density 3.589%

    No Known Activations