© 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. 15787
    Prev
    Next
    INDEX
    Explanations

    greetings or salutations in the text

    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
     InputDecoration
    -0.81
     يتيمه
    -0.79
    tagHelperRunner
    -0.76
     Daniels
    -0.74
    LookAnd
    -0.72
    談社
    -0.69
     متعلقه
    -0.68
    KommentareTeilen
    -0.67
    ReusableCell
    -0.67
    XmlAccessorType
    -0.66
    POSITIVE LOGITS
    hi
    2.85
     Hi
    2.32
     hi
    2.28
    HI
    2.26
    Hi
    2.25
     HI
    2.05
     Hiram
    1.30
    hihi
    1.30
     Hipp
    1.26
    hii
    1.26
    Activations Density 0.059%

    No Known Activations