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. 792
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to history and historical study

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

    starting with "hist" related to history

    np_acts-logits-general · gemini-2.0-flash

    history of specific subjects

    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
     myſelf
    -0.90
    IsContent
    -0.89
     himſelf
    -0.87
    Rujuakan
    -0.86
    AddTagHelper
    -0.84
     Shakspeare
    -0.84
     itſelf
    -0.83
    MigrationBuilder
    -0.80
    peño
    -0.80
     theſe
    -0.76
    POSITIVE LOGITS
    prepareStatement
    0.54
    چه
    0.52
    Prés
    0.52
     Zwar
    0.47
     past
    0.45
     boyunca
    0.45
    itus
    0.45
    悠
    0.43
     panjang
    0.43
    edi
    0.43
    Activations Density 0.223%

    No Known Activations