© 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-2-9B
    7. Residual Stream - 16k
    9. 35-GEMMASCOPE-RES-16K
    11. 12479
    Prev
    Next
    INDEX
    Explanations

    phrases or structures indicating emphasis or exclamation

    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
    Biografía
    -0.42
     minuter
    -0.34
    moveToNext
    -0.34
     MCS
    -0.34
    adpleegd
    -0.32
     simul
    -0.31
     LSM
    -0.31
    ┃
    -0.31
    navigationItem
    -0.30
     üzere
    -0.30
    POSITIVE LOGITS
     hell
    3.23
     heck
    2.63
     Hell
    2.50
     HELL
    2.50
    Hell
    2.44
    hell
    2.36
    HELL
    2.13
    Heck
    1.81
    heck
    1.76
     Heck
    1.70
    Activations Density 0.251%

    No Known Activations