© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 5634
    Prev
    Next
    INDEX
    Explanations

    programming or coding syntax, particularly in the context of data handling or conditional statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Jody
    -0.81
     Finney
    -0.80
    Jody
    -0.72
     Arturo
    -0.71
     Silber
    -0.66
     Bork
    -0.65
     FCS
    -0.64
     Hann
    -0.64
     Castro
    -0.64
     Milner
    -0.63
    POSITIVE LOGITS
     nakalista
    0.94
     Jaco
    0.73
     Jacob
    0.73
     Erik
    0.72
    Erik
    0.71
     Jennifer
    0.71
    Jacob
    0.70
     Gibbon
    0.69
     Helen
    0.69
     Davison
    0.66
    Activations Density 1.337%

    No Known Activations