© 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. 8730
    Prev
    Next
    INDEX
    Explanations

    elements related to legal proceedings and structured formats, like evidence and documentation

    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
     للاسماء
    -1.02
     فريبيس
    -0.96
     otomatig
    -0.95
    новништво
    -0.86
     queſta
    -0.79
    StoryboardSegue
    -0.77
     noqa
    -0.77
    ロウィン
    -0.76
    aarrggbb
    -0.75
     パンチラ
    -0.74
    POSITIVE LOGITS
     following
    0.84
     folgende
    0.68
     folgendes
    0.65
    如下
    0.64
    以下
    0.64
     folgenden
    0.62
    は以下の
    0.59
    following
    0.57
    以下の
    0.57
     Following
    0.56
    Activations Density 0.831%

    No Known Activations