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. 18-GEMMASCOPE-RES-16K
    6. 94
    Prev
    Next
    INDEX
    Explanations

    key medical terms and phrases associated with unmet medical needs and various medical conditions

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

    "Market" or "opportunity"

    np_acts-logits-general · gemini-2.0-flash

    market opportunity potential growth

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Efq
    -0.66
     متعلقه
    -0.63
    VertexAttrib
    -0.63
     يتيمه
    -0.61
     myſelf
    -0.59
     purpoſe
    -0.59
    ніципа
    -0.58
     pinulongan
    -0.58
     uſed
    -0.57
     Monfieur
    -0.57
    POSITIVE LOGITS
     market
    1.40
     opportunity
    1.10
     Market
    1.08
    market
    1.08
     marché
    1.06
     potential
    1.04
    Market
    1.02
     MARKET
    1.01
     niche
    0.98
     opportunities
    0.97
    Activations Density 0.220%

    No Known Activations