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. 14-GEMMASCOPE-RES-16K
    6. 214
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to employment contracts and their stipulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    expandindo
    -0.66
     kaarangay
    -0.59
    BeginContext
    -0.57
    RTEE
    -0.54
     Wikimedijinoj
    -0.52
     ProtoMessage
    -0.50
    afficheront
    -0.50
     Roskov
    -0.48
    appliquer
    -0.48
     APPELLATE
    -0.46
    POSITIVE LOGITS
     contd
    0.64
     general
    0.59
     algemeen
    0.56
    general
    0.56
    ForKey
    0.55
     Umgang
    0.54
    `{.
    0.54
     considerations
    0.54
     يتيمه
    0.54
    eneral
    0.53
    Activations Density 0.669%

    No Known Activations