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. 24-GEMMASCOPE-RES-16K
    6. 14131
    Prev
    Next
    INDEX
    Explanations

    formal financial and administrative language related to projects and planning

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

    Sentences that end with a period

    np_acts-logits-general · gemini-2.0-flash

    plans, negotiations, discussions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    voorbeeld
    -0.85
     parfois
    -0.65
     ejemplo
    -0.62
     souvent
    -0.61
     veces
    -0.59
     vezes
    -0.58
     specialmente
    -0.57
    flashdata
    -0.56
     például
    -0.56
     estekak
    -0.55
    POSITIVE LOGITS
     negotiations
    1.10
     plans
    1.07
     work
    1.07
    Plans
    1.03
     Plans
    1.01
     Negotiations
    1.01
     discussions
    0.95
     preparations
    0.92
    Discussions
    0.91
    plans
    0.91
    Activations Density 0.422%

    No Known Activations