© 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-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 15148
    Prev
    Next
    INDEX
    Explanations

    closing curly braces in code or programming contexts

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

    Code-related tokens: "else", curly braces, parentheses

    np_acts-logits-general · gemini-2.0-flash

    resistance against

    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
    RectangleBorder
    -0.56
    (.*
    -0.54
    paž
    -0.54
     للمعارف
    -0.53
    {\
    -0.51
     transfieras
    -0.51
    zenta
    -0.50
     Hinton
    -0.50
    (
    -0.48
     jspb
    -0.47
    POSITIVE LOGITS
     else
    1.05
    else
    0.96
    '}
    0.86
    "}
    0.81
    }))
    0.80
    .*")]
    0.78
    contentLoaded
    0.78
    "}"
    0.77
    })}
    0.76
    }}}
    0.76
    Activations Density 0.101%

    No Known Activations