© 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. 2-GEMMASCOPE-RES-16K
    11. 12244
    Prev
    Next
    INDEX
    Explanations

    phrases related to decision-making processes

    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
    ロウィン
    -0.78
    EndContext
    -0.78
     beſte
    -0.77
    GIVEREF
    -0.77
     beſch
    -0.76
     ſind
    -0.76
    <unused52>
    -0.75
    rungsseite
    -0.75
    <unused8>
    -0.75
    [@BOS@]
    -0.75
    POSITIVE LOGITS
     advised
    0.41
     recommended
    0.38
     suggested
    0.38
     aim
    0.37
     ideal
    0.34
     aconse
    0.34
    obiettivo
    0.34
     advises
    0.33
     aimed
    0.32
    建议
    0.32
    Activations Density 0.859%

    No Known Activations