Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 2485
    Prev
    Next
    INDEX
    Explanations

    terms related to amplification processes in scientific contexts

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

    starting with "amp" and related to amplification

    np_acts-logits-general · gemini-2.0-flash

    words starting with "amp"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rouvez
    -0.69
    owitz
    -0.52
    keo
    -0.50
    ็จ
    -0.49
     venuto
    -0.48
     douane
    -0.48
     parseFrom
    -0.48
    zzar
    -0.47
    ostar
    -0.46
     heavy
    -0.46
    POSITIVE LOGITS
     Amp
    1.02
    Amp
    0.92
     amp
    0.91
     amplify
    0.86
     amplification
    0.82
     Amphi
    0.80
     amplifiers
    0.80
     amps
    0.79
     AMP
    0.78
     Amplifier
    0.75
    Activations Density 0.098%

    No Known Activations