© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. MLP Out - 16k
    5. 19-GEMMASCOPE-MLP-16K
    6. 6817
    Prev
    Next
    INDEX
    Explanations

    programming syntax and function calls

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-mlp-16k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_19/width_16k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_mlp_out
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     catch
    -3.00
     catching
    -2.72
     Catch
    -2.63
    catch
    -2.58
     catches
    -2.50
     caught
    -2.39
     CATCH
    -2.36
    Catch
    -2.33
    catching
    -2.17
    caught
    -2.09
    POSITIVE LOGITS
    Buildable
    0.48
     McClure
    0.44
     endregion
    0.42
     Tees
    0.42
     Adkins
    0.41
    olstein
    0.40
     sklo
    0.40
    ENS
    0.40
    ENSA
    0.40
    SEM
    0.39
    Activations Density 0.362%

    No Known Activations