© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 13026
    Prev
    Next
    INDEX
    Explanations

    phrases related to runaway events or conditions, particularly in healthcare or biological contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    uncontrolled runaway process

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     genoeg
    -0.43
     pijn
    -0.42
     düşük
    -0.41
    çoivent
    -0.41
     Shorter
    -0.41
     Relaciones
    -0.41
     temporaire
    -0.40
     shorter
    -0.40
    мень
    -0.40
    Pause
    -0.39
    POSITIVE LOGITS
     runaway
    1.14
     uncontrolled
    1.11
     uncontrollable
    0.92
     uncontrol
    0.89
     unchecked
    0.78
     overrun
    0.75
     unbounded
    0.73
     excessive
    0.72
     exces
    0.70
     prolifer
    0.69
    Activations Density 0.190%

    No Known Activations