© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 2958
    Prev
    Next
    INDEX
    Explanations

    terms related to innovation and research funding in the scientific and technological sectors

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

    Research, development, and innovation

    np_acts-logits-general · gemini-2.0-flash

    research and innovation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FormTagHelper
    -0.55
     ModelExpression
    -0.49
    IntoConstraints
    -0.43
    อนไลน์
    -0.42
     afge
    -0.40
    omla
    -0.39
    hobo
    -0.39
    dbus
    -0.39
    այ
    -0.39
    Errors
    -0.38
    POSITIVE LOGITS
     innovation
    1.39
     research
    1.36
     Innovation
    1.27
     Research
    1.26
    Innovation
    1.21
    innovation
    1.20
    Research
    1.19
    research
    1.18
     Invention
    1.15
     inventions
    1.10
    Activations Density 0.289%

    No Known Activations