© 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-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 8479
    Prev
    Next
    INDEX
    Explanations

    phrases related to trading strategies and market analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Saltar
    -0.48
     adequacy
    -0.47
     casera
    -0.47
     Parece
    -0.46
     sufficiency
    -0.45
     legitimacy
    -0.45
     Portanto
    -0.45
    ğından
    -0.45
     bruto
    -0.45
     soundness
    -0.44
    POSITIVE LOGITS
     melakukan
    0.65
     men
    0.63
     ProtoMessage
    0.63
     menge
    0.62
     meme
    0.62
    bringing
    0.61
     delivering
    0.61
     meng
    0.60
     bringing
    0.59
     menyal
    0.59
    Activations Density 0.044%

    No Known Activations