© 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. 34-GEMMASCOPE-RES-16K
    6. 11760
    Prev
    Next
    INDEX
    Explanations

    symbols and special characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ädie
    -0.46
    HasForeignKey
    -0.43
    VersionUID
    -0.41
     butterknife
    -0.40
     دیکھیے
    -0.37
     le
    -0.37
    cstring
    -0.37
    getActiveSheet
    -0.37
    Портали
    -0.36
    Попис
    -0.36
    POSITIVE LOGITS
    -------
    0.52
     للمعارف
    0.51
    httphttps
    0.47
    OGND
    0.45
    oa̍t
    0.41
    :✨
    0.40
    Tikang
    0.40
    verifyException
    0.39
     Too
    0.39
    lya
    0.38
    Activations Density 0.092%

    No Known Activations