© 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. 20-GEMMASCOPE-RES-16K
    11. 70
    Prev
    Next
    INDEX
    Explanations

    situations involving blame and accountability

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

    preceding an exception or blame

    np_acts-logits-general · gemini-2.0-flash

    except or exception

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TagMode
    -0.60
     Waray
    -0.58
     للاسماء
    -0.57
     magasiner
    -0.54
    parsedMessage
    -0.53
     StatefulWidget
    -0.53
    Personendaten
    -0.52
    MessageOf
    -0.51
    ernalia
    -0.51
    rigley
    -0.51
    POSITIVE LOGITS
     except
    3.64
    except
    3.38
     Except
    3.16
    Except
    3.12
     EXCEPT
    2.79
     excepto
    2.76
     exception
    2.65
     kecuali
    2.60
     sauf
    2.56
    EXCEPT
    2.53
    Activations Density 1.157%

    No Known Activations