© 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. 21-GEMMASCOPE-RES-16K
    6. 14709
    Prev
    Next
    INDEX
    Explanations

    references to assessments and evaluations in a research or educational context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Roskov
    -0.71
    WriteTagHelper
    -0.69
    yntaxException
    -0.64
    Havolalar
    -0.63
     HttpNotFound
    -0.63
    MediaStore
    -0.62
    AddTagHelper
    -0.57
    Tikang
    -0.57
     montón
    -0.55
    RegressionTest
    -0.55
    POSITIVE LOGITS
     additional
    1.18
    additional
    0.97
     sufficient
    0.95
     an
    0.95
     considerable
    0.93
     appropriate
    0.91
     adequate
    0.90
     a
    0.89
     significant
    0.87
     substantial
    0.86
    Activations Density 1.036%

    No Known Activations