© 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-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 14555
    Prev
    Next
    INDEX
    Explanations

    blocks of code, particularly focusing on structure and flow control statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    closing braces of try-catch blocks.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     otherwise
    -0.82
     Otherwise
    -0.73
    Otherwise
    -0.71
     OTHERWISE
    -0.63
    otherwise
    -0.60
    else
    -0.56
     else
    -0.53
     sonst
    -0.52
     jinak
    -0.46
    不然
    -0.46
    POSITIVE LOGITS
     catch
    1.78
    catch
    1.53
     Catch
    1.51
     CATCH
    1.35
    Catch
    1.35
    CATCH
    1.30
     catching
    1.29
     catches
    1.25
    Catching
    1.05
     caught
    1.04
    Activations Density 0.074%

    No Known Activations