© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 8003
    Prev
    Next
    INDEX
    Explanations

    occurrences of error handling keywords in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itola
    -0.38
    WriteBarrier
    -0.37
     utafitiHapana
    -0.36
     Pli
    -0.36
     monop
    -0.35
    kanen
    -0.35
     limo
    -0.34
    }{*}{
    -0.33
    prm
    -0.32
    kian
    -0.32
    POSITIVE LOGITS
     catch
    4.09
     Catch
    3.69
     catching
    3.53
    Catch
    3.44
    catch
    3.44
     catches
    3.42
     CATCH
    3.30
     caught
    2.92
    CATCH
    2.88
    Catching
    2.77
    Activations Density 0.087%

    No Known Activations