© 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. 35-GEMMASCOPE-RES-16K
    11. 10226
    Prev
    Next
    INDEX
    Explanations

    mathematical notations and symbols related to functions and equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    \:
    -0.46
    \;
    -0.41
    \|
    -0.41
    \|\
    -0.40
    hdashline
    -0.39
    xymatrix
    -0.37
    GenerationType
    -0.35
    \,
    -0.35
    formik
    -0.35
     literature
    -0.34
    POSITIVE LOGITS
    Personendaten
    0.68
    PerformLayout
    0.60
     Roskov
    0.56
    texts
    0.55
     OFDb
    0.55
    left
    0.55
     PyTuple
    0.54
    text
    0.54
    mathrm
    0.52
     MutableLiveData
    0.52
    Activations Density 1.641%

    No Known Activations