Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 27-GEMMASCOPE-RES-16K
    6. 9829
    Prev
    Next
    INDEX
    Explanations

    actions related to arrests and judicial decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     InputDecoration
    -0.27
     Сара
    -0.26
    ξύ
    -0.26
     peix
    -0.26
    pplung
    -0.26
    rollup
    -0.25
    lös
    -0.24
     conferencia
    -0.24
    folgen
    -0.24
     straw
    -0.24
    POSITIVE LOGITS
     halted
    1.59
     stopped
    1.49
     halt
    1.46
     stop
    1.43
     paused
    1.42
     stoppage
    1.41
     stopping
    1.38
     pause
    1.37
     STOP
    1.37
     stops
    1.36
    Activations Density 0.431%

    No Known Activations