© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 12727
    Prev
    Next
    INDEX
    Explanations

    expressions that indicate extreme negativity or failure

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

    worst of / worst case

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ipro
    -0.66
    thâu
    -0.66
    Autoritní
    -0.64
     ligiloj
    -0.62
    ⟬
    -0.61
     typelib
    -0.60
    ean
    -0.58
    iibo
    -0.57
     transfieras
    -0.57
    ReusableCell
    -0.57
    POSITIVE LOGITS
     worst
    1.80
    worst
    1.69
    Worst
    1.55
     Worst
    1.54
     peores
    1.00
     peor
    0.96
     pior
    0.89
     WOR
    0.84
     deadliest
    0.83
    最悪
    0.82
    Activations Density 0.005%

    No Known Activations