© 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. 18-GEMMASCOPE-RES-16K
    6. 3306
    Prev
    Next
    INDEX
    Explanations

    details related to financial transactions, particularly in the context of baseball statistics and contract information

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

    ERA, friction, or cost reduction

    np_acts-logits-general · gemini-2.0-flash

    lowering costs

    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
    zahlen
    -0.52
    joner
    -0.48
    neta
    -0.47
    ayet
    -0.46
    Amplitude
    -0.44
    chell
    -0.42
    бия
    -0.42
    ากาศ
    -0.41
     BufferedWriter
    -0.40
    ortun
    -0.40
    POSITIVE LOGITS
    costs
    0.95
     costs
    0.92
    Costs
    0.92
     '\\;'
    0.90
     cost
    0.89
     Costs
    0.88
    cost
    0.84
     lowering
    0.84
     Lowest
    0.83
    Cost
    0.83
    Activations Density 0.339%

    No Known Activations