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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 6447
    Prev
    Next
    INDEX
    Explanations

    terms related to insolvency and financial distress

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

    The token "Ins" followed by various suffixes

    np_acts-logits-general · gemini-2.0-flash

    words starting with Ins

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Centrale
    -0.68
     Picchu
    -0.66
     Pyle
    -0.64
    kates
    -0.63
     Vikipedi
    -0.62
    ALLEL
    -0.62
     Twit
    -0.62
     McNally
    -0.61
    icles
    -0.61
     Bá
    -0.60
    POSITIVE LOGITS
     Ins
    1.31
    Ins
    1.14
    ins
    1.03
     INS
    0.95
     ins
    0.90
    Insulin
    0.85
    INS
    0.84
     insulation
    0.83
     onOptions
    0.82
     insurg
    0.82
    Activations Density 0.280%

    No Known Activations