© 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-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 2196
    Prev
    Next
    INDEX
    Explanations

    string delimiters and function call syntax in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 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
     onOptions
    -1.00
    ?>">
    -0.98
    "]}
    -0.80
     Patt
    -0.79
    "]).
    -0.79
    "]=
    -0.77
    "]:
    -0.75
    })]
    -0.74
    findpost
    -0.74
    <>());
    -0.74
    POSITIVE LOGITS
    er
    0.84
     Gilman
    0.80
    rinology
    0.78
     (“
    0.76
     crystall
    0.72
     Gonçalves
    0.70
    °•
    0.70
    👍👍
    0.69
     Requiem
    0.68
    ••••
    0.67
    Activations Density 0.200%

    No Known Activations