© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 10343
    Prev
    Next
    INDEX
    Explanations

    elements related to data fetching and manipulation in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/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.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
     typelib
    -0.65
     ब्रेकडाउन
    -0.60
    OGND
    -0.58
     يتيمه
    -0.57
    LocationManager
    -0.51
    __":
    -0.49
    NUMX
    -0.49
    évaluateur
    -0.48
    EndContext
    -0.47
     arşivlendi
    -0.46
    POSITIVE LOGITS
    ariConfig
    0.63
     InputDecoration
    0.54
     initComponents
    0.51
    initComponents
    0.46
     Reglamento
    0.44
     gouvern
    0.44
     Pfalz
    0.42
     francès
    0.42
    équipement
    0.42
     Properties
    0.41
    Activations Density 0.441%

    No Known Activations