© 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. 1-GEMMASCOPE-RES-16K
    11. 7620
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "Bean" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     OFDb
    -0.91
     Administrativna
    -0.76
     initComponents
    -0.74
    fromnode
    -0.72
     للمعارف
    -0.71
    ClientSize
    -0.70
    ContentAsync
    -0.69
    Rohy
    -0.69
     ProtoMessage
    -0.68
    IVEREF
    -0.67
    POSITIVE LOGITS
     mold
    1.44
     mould
    1.26
    mold
    1.23
     Mold
    1.16
     molds
    1.12
    Mold
    1.05
     moulds
    1.02
     Mould
    1.01
     molding
    0.92
     moulding
    0.87
    Activations Density 0.120%

    No Known Activations