© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 1578
    Prev
    Next
    INDEX
    Explanations

    syntactical elements and structural components in programming languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code assignment and operators

    np_acts-logits-general · gemini-2.0-flash

    programming assignments and greek letters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bezeichneter
    -0.69
     Vil
    -0.64
    EndProject
    -0.63
    Punk
    -0.61
     Shenandoah
    -0.61
     Clegg
    -0.61
     Punk
    -0.60
     Whittaker
    -0.59
     Sasuke
    -0.59
     Mimi
    -0.59
    POSITIVE LOGITS
     Lynch
    0.81
     Kroger
    0.73
    Lynch
    0.72
     Curtis
    0.68
     Redmond
    0.67
     Murray
    0.66
     Latch
    0.65
     Michi
    0.65
    latch
    0.65
     Morris
    0.65
    Activations Density 0.814%

    No Known Activations