Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 9974
    Prev
    Next
    INDEX
    Explanations

    references to negotiation and bidding processes in competitive situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    出版年
    -0.69
    ovna
    -0.55
    BASEPATH
    -0.51
    ագրություններ
    -0.51
    CppCodeGen
    -0.50
     punishable
    -0.47
     insuffisamment
    -0.47
    ijen
    -0.47
    wieś
    -0.46
    Autowired
    -0.46
    POSITIVE LOGITS
     negotiators
    1.07
    Negoti
    1.06
     negotiating
    1.05
     negotiation
    1.04
     negotiations
    1.03
    negoti
    1.01
     negotiate
    0.99
     negotiator
    0.99
     negotiated
    0.98
     Negotiations
    0.96
    Activations Density 0.206%

    No Known Activations