© 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-2-9B
    7. Residual Stream - 16k
    9. 37-GEMMASCOPE-RES-16K
    11. 4746
    Prev
    Next
    INDEX
    Explanations

    closing curly braces in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :✨
    -0.70
    exitRule
    -0.67
     الحره
    -0.58
    ArrowToggle
    -0.57
    WriteTagHelper
    -0.54
    thenReturn
    -0.51
     للاسماء
    -0.50
    angliski
    -0.50
    Життєпис
    -0.49
    ंदीखरीदारी
    -0.47
    POSITIVE LOGITS
     catch
    0.93
    catch
    0.82
     Catch
    0.53
     CATCH
    0.49
     cat
    0.49
    Catch
    0.46
     caveat
    0.45
    except
    0.45
     catchment
    0.43
     Cat
    0.43
    Activations Density 0.082%

    No Known Activations