© 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. 24-GEMMASCOPE-RES-16K
    11. 3911
    Prev
    Next
    INDEX
    Explanations

    structured data formats and their definitions

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

    Reference to a figure or table

    np_acts-logits-general · gemini-2.0-flash

    references with hash identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Fermi
    -0.61
    databind
    -0.60
     Cros
    -0.58
     Ferri
    -0.58
     Tind
    -0.58
     Lansing
    -0.57
     GCM
    -0.56
    Fermi
    -0.55
     TCM
    -0.55
     CMC
    -0.54
    POSITIVE LOGITS
    ;#
    1.14
     ##
    1.13
     "#
    1.09
    "#
    1.09
     '#
    1.08
    -#
    1.07
    ##
    1.07
     (#
    1.07
    ("#
    1.06
    ","#
    1.06
    Activations Density 0.922%

    No Known Activations