© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 4092
    Prev
    Next
    INDEX
    Explanations

    numerical values and their conversions, particularly related to time and measurement units

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    data
    -0.36
    味
    -0.35
     Fast
    -0.35
    Unlock
    -0.34
    oma
    -0.34
    oor
    -0.34
     or
    -0.34
    onec
    -0.34
    ServerSocket
    -0.33
    $_['
    -0.33
    POSITIVE LOGITS
    AddTagHelper
    1.03
     Normdatei
    1.00
     الحره
    0.93
     BoxFit
    0.92
     autorytatywna
    0.87
    ագրություններ
    0.86
     linkovi
    0.85
    __':
    0.80
    Carriera
    0.80
     ujednoznacz
    0.80
    Activations Density 0.797%

    No Known Activations