© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 22-GEMMASCOPE-RES-16K
    11. 3201
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and expressions

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

    Separators in lists of numbers or symbols

    np_acts-logits-general · gemini-2.0-flash

    delimiters and quoted items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :
    -0.56
     sa
    -0.55
     Bel
    -0.53
     co
    -0.53
    -
    -0.53
    BASEPATH
    -0.52
     sem
    -0.51
     Se
    -0.51
     pre
    -0.51
     par
    -0.49
    POSITIVE LOGITS
    etc
    1.25
     etc
    1.20
     Roskov
    1.13
     themſelves
    1.05
     myſelf
    1.04
     pleaſure
    1.03
     itſelf
    1.02
     '\\;'
    1.01
    DockStyle
    1.00
    IntoConstraints
    0.99
    Activations Density 1.140%

    No Known Activations