© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 6434
    Prev
    Next
    INDEX
    Explanations

    syntactic structures and grammatical components in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     
    -0.62
    ↵↵
    -0.52
    IALS
    -0.50
    aleigh
    -0.50
    ITES
    -0.49
    mering
    -0.49
    iali
    -0.48
    tuan
    -0.48
    ivar
    -0.47
    UEL
    -0.46
    POSITIVE LOGITS
     disambiguazione
    0.64
     ujednoznacz
    0.59
    Rüyada
    0.47
    Personendaten
    0.46
    例文
    0.44
     Wiktionnaire
    0.43
    ValueStyle
    0.43
     tramonto
    0.43
     صوتيه
    0.42
     explotación
    0.41
    Activations Density 1.856%

    No Known Activations