© 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. 23-GEMMASCOPE-RES-16K
    6. 6861
    Prev
    Next
    INDEX
    Explanations

    variables and method definitions in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Vidite
    -0.92
     المعيارى
    -0.74
    /*
    -0.70
     Roskov
    -0.66
    ItemBackground
    -0.66
    URLException
    -0.65
     يتيمه
    -0.64
     OFDb
    -0.63
    WireFormat
    -0.62
    ="#"><
    -0.61
    POSITIVE LOGITS
    atalos
    0.49
    ponses
    0.47
    ModelSerializer
    0.43
    araf
    0.43
    libre
    0.42
     comets
    0.42
    ię
    0.42
    של
    0.42
    pital
    0.42
    prnewswire
    0.40
    Activations Density 0.603%

    No Known Activations