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. 1-GEMMASCOPE-RES-16K
    6. 14844
    Prev
    Next
    INDEX
    Explanations

    terms related to raising or increasing something, particularly in the context of fundraising or similar activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CURIAM
    -0.64
    достатки
    -0.58
     henkil
    -0.58
    interopRequire
    -0.57
     estekak
    -0.57
     değiş
    -0.54
    abancı
    -0.54
     jPanel
    -0.53
    PICT
    -0.52
    ịch
    -0.52
    POSITIVE LOGITS
     raise
    4.49
     raising
    4.28
     Raise
    4.12
     Raising
    4.04
     raised
    4.03
     raises
    3.94
    Raising
    3.94
    Raise
    3.76
    raise
    3.73
    raising
    3.70
    Activations Density 0.074%

    No Known Activations