© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 13730
    Prev
    Next
    INDEX
    Explanations

    closing braces in code syntax

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

    Code blocks with "catch" statements

    np_acts-logits-general · gemini-2.0-flash

    exception handling blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adpleegd
    -0.73
    SequentialGroup
    -0.72
    TagMode
    -0.71
    awtextra
    -0.71
     others
    -0.69
    __(/*!
    -0.68
     elif
    -0.68
     Others
    -0.67
    bewerken
    -0.66
     else
    -0.66
    POSITIVE LOGITS
     catch
    2.04
    catch
    1.85
     Catch
    1.43
    Catch
    1.30
     catching
    1.30
     catches
    1.29
     CATCH
    1.29
     caught
    1.18
    CATCH
    1.10
    caught
    1.00
    Activations Density 0.035%

    No Known Activations