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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 4135
    Prev
    Next
    INDEX
    Explanations

    technical details regarding video frame rates and conversion processes

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

    Values or parameters related to rates or speeds

    np_acts-logits-general · gemini-2.0-flash

    rate values

    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
     autorytatywna
    -0.64
    complexType
    -0.63
     resourceCulture
    -0.60
     ujednoznacz
    -0.58
     propOrder
    -0.57
    Personensuche
    -0.56
    saraba
    -0.55
    waite
    -0.53
     viewType
    -0.52
    enumi
    -0.52
    POSITIVE LOGITS
     rate
    1.00
     Rate
    0.89
     speeds
    0.89
    Rate
    0.88
     speed
    0.87
    rate
    0.86
     RATE
    0.85
     rates
    0.82
     slowest
    0.81
     slowed
    0.80
    Activations Density 0.261%

    No Known Activations