© 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. 21-GEMMASCOPE-RES-16K
    11. 194
    Prev
    Next
    INDEX
    Explanations

    terms associated with research methodologies and scientific analysis

    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
    RegressionTest
    -0.59
    ngdoc
    -0.58
     resourceCulture
    -0.57
    hdashline
    -0.56
    Santis
    -0.52
    vaného
    -0.52
    volles
    -0.52
     تانيه
    -0.51
    ']>;
    -0.51
    sätzlich
    -0.51
    POSITIVE LOGITS
     these
    3.96
    these
    3.45
     These
    3.29
    These
    3.27
     THESE
    2.89
    これらの
    2.79
    这些
    2.70
    這些
    2.69
     those
    2.48
     этих
    2.45
    Activations Density 2.146%

    No Known Activations