© 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. 12416
    Prev
    Next
    INDEX
    Explanations

    expressions indicating requests for information or assistance

    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
    DockStyle
    -0.47
    inSlope
    -0.46
     говорю
    -0.43
    让他们
    -0.43
     I
    -0.42
    讓他
    -0.41
     گفتم
    -0.39
    keyColumn
    -0.39
    ніципалі
    -0.38
    让她
    -0.38
    POSITIVE LOGITS
     me
    3.16
    me
    1.70
     меня
    1.61
     мне
    1.43
     comigo
    1.40
     Me
    1.37
     mnie
    1.36
    Me
    1.36
     us
    1.34
     meille
    1.30
    Activations Density 0.599%

    No Known Activations