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. 18-GEMMASCOPE-RES-16K
    6. 3115
    Prev
    Next
    INDEX
    Explanations

    references to fees and financial costs related to services

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

    after "fee" or referring to fees/payments

    np_acts-logits-general · gemini-2.0-flash

    fees and payments

    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
     Des
    -0.47
    حداث
    -0.45
     координа
    -0.42
     Hou
    -0.42
     Mer
    -0.41
    tuan
    -0.41
    手中
    -0.41
    (',')
    -0.40
     God
    -0.40
     فريبيس
    -0.39
    POSITIVE LOGITS
     payable
    1.06
     levied
    1.06
     متعلقه
    1.01
     incurred
    0.98
     Payable
    0.83
     payments
    0.82
    MLLoader
    0.77
     amounting
    0.77
    payable
    0.75
     amounts
    0.74
    Activations Density 0.241%

    No Known Activations