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. 2-GEMMASCOPE-RES-16K
    6. 6598
    Prev
    Next
    INDEX
    Explanations

    technical terms and specifications related to computer memory and engineering

    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
    ülete
    -0.56
    apimachinery
    -0.48
    valt
    -0.47
    yectos
    -0.45
    pya
    -0.45
     Initialized
    -0.45
     FishBase
    -0.44
    kter
    -0.44
    #}
    -0.44
     IndexPath
    -0.43
    POSITIVE LOGITS
    Personensuche
    0.81
     Económica
    0.64
    олові
    0.58
    copg
    0.58
    😍😍
    0.57
    Gambas
    0.56
    exitRule
    0.56
    ModelBuilder
    0.56
     Manne
    0.55
    adpleegd
    0.55
    Activations Density 3.008%

    No Known Activations