© 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. 23-GEMMASCOPE-RES-16K
    11. 5085
    Prev
    Next
    INDEX
    Explanations

    terms related to law, governance, and conflict

    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
     resourceCulture
    -1.06
    XmlAccessType
    -0.94
    featureID
    -0.91
    WriteBarrier
    -0.90
    InjectAttribute
    -0.90
    Datuak
    -0.89
    Personendaten
    -0.88
    EndProject
    -0.86
    CppMethod
    -0.85
    AndEndTag
    -0.83
    POSITIVE LOGITS
    fs
    0.45
    pricht
    0.40
    p
    0.38
    gs
    0.37
    fstream
    0.37
    g
    0.36
    ts
    0.36
    f
    0.34
    bs
    0.34
     Wald
    0.33
    Activations Density 0.416%

    No Known Activations