© 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-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 10563
    Prev
    Next
    INDEX
    Explanations

    references to stocks or stock-related terms

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

    "stock" followed by various words

    np_acts-logits-general · gemini-2.0-flash

    stock followed by noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    drawal
    -0.57
    SourceChecksum
    -0.55
    WriteTagHelper
    -0.55
     continuant
    -0.55
     LUMP
    -0.53
    ParallelGroup
    -0.53
    urende
    -0.53
     Kiz
    -0.53
    çalves
    -0.52
     Wayback
    -0.52
    POSITIVE LOGITS
    piles
    0.82
     }}"></
    0.68
    afficheront
    0.65
    pile
    0.63
    broker
    0.63
     mostrarán
    0.62
    p
    0.61
    లాలు
    0.59
    holms
    0.58
     ControllerBase
    0.57
    Activations Density 0.076%

    No Known Activations