© 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. 23-GEMMASCOPE-RES-16K
    11. 8612
    Prev
    Next
    INDEX
    Explanations

    references to terrorism and related security issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/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.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     (
    -0.35
    </h5>
    -0.34
    UnifiedTopology
    -0.32
     เค
    -0.31
       
    -0.31
    本
    -0.31
     static
    -0.31
    ↵↵↵
    -0.30
    上
    -0.29
     #
    -0.29
    POSITIVE LOGITS
     EconPapers
    0.90
    enterOuterAlt
    0.88
    ⟬
    0.85
     invokingState
    0.83
    CppMethod
    0.80
     Reſ
    0.79
    Vidite
    0.77
    <unused74>
    0.76
    <unused8>
    0.76
    [@BOS@]
    0.76
    Activations Density 3.075%

    No Known Activations