© 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-2-9B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 4286
    Prev
    Next
    INDEX
    Explanations

    expressions of hope and expectation

    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
     spores
    -0.36
     will
    -0.36
     μην
    -0.33
     dedans
    -0.30
     arriba
    -0.29
    里面
    -0.29
    __)
    -0.28
     hayas
    -0.28
     zostanie
    -0.28
    MOUS
    -0.27
    POSITIVE LOGITS
     would
    0.82
    ########.
    0.77
    would
    0.75
    Would
    0.75
     Would
    0.70
     nahilalakip
    0.69
    transQ
    0.66
     WOULD
    0.65
     wäre
    0.63
     serait
    0.63
    Activations Density 0.248%

    No Known Activations