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. 15-GEMMASCOPE-RES-16K
    6. 8548
    Prev
    Next
    INDEX
    Explanations

    terms and references related to gold and its varieties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     compri
    -0.76
     Dishwasher
    -0.69
    mListener
    -0.63
     TestBed
    -0.63
    readline
    -0.62
     Slaughter
    -0.62
     pstmt
    -0.61
    viewpager
    -0.61
    pyplot
    -0.61
    Dishwasher
    -0.61
    POSITIVE LOGITS
     gold
    1.33
     Gold
    1.26
     GOLD
    1.24
    Gold
    1.15
    gold
    1.15
     golden
    1.12
    GOLD
    1.11
    golden
    1.10
     Golden
    1.07
    Golden
    1.02
    Activations Density 0.113%

    No Known Activations