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. 19-GEMMASCOPE-RES-16K
    6. 15642
    Prev
    Next
    INDEX
    Explanations

    references to money management and saving strategies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    setVerticalGroup
    -0.59
    apparent
    -0.48
    ublic
    -0.48
     createState
    -0.46
    qtype
    -0.45
    openqa
    -0.45
     CommandType
    -0.45
    SerializedSize
    -0.45
    giri
    -0.45
    enterOuterAlt
    -0.44
    POSITIVE LOGITS
     savings
    1.42
     saving
    1.20
     Savings
    1.13
     saved
    1.12
    savings
    1.11
    Savings
    1.06
     reserve
    1.03
     Saving
    1.01
     SAVINGS
    0.99
    Saving
    0.95
    Activations Density 0.135%

    No Known Activations