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. 8707
    Prev
    Next
    INDEX
    Explanations

    phrases related to outsourcing and data privacy

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

    Transferring or selling something

    np_acts-logits-general · gemini-2.0-flash

    transfer or give

    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
    脚注の使い方
    -0.55
    CodedInputStream
    -0.54
    inplace
    -0.51
    LayoutStyle
    -0.48
    SharedCtor
    -0.47
    Carriera
    -0.47
    Gweler
    -0.45
     comport
    -0.44
    MockMvc
    -0.44
     MonoBehaviour
    -0.44
    POSITIVE LOGITS
     handed
    0.99
     handing
    0.94
     kepada
    0.93
     handover
    0.90
     переда
    0.85
     sell
    0.83
     sold
    0.81
     forwarded
    0.79
    送给
    0.77
    交给
    0.76
    Activations Density 0.366%

    No Known Activations