© 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. 2-GEMMASCOPE-RES-16K
    6. 5457
    Prev
    Next
    INDEX
    Explanations

    words related to various forms of creative expressions

    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
    djangoproject
    -0.61
    Gemeinden
    -0.59
     múl
    -0.56
    WAUKEE
    -0.54
     Huerta
    -0.54
     Schulz
    -0.53
    eburger
    -0.53
    pozdrawiam
    -0.52
    Història
    -0.51
    abstractmethod
    -0.51
    POSITIVE LOGITS
    ings
    3.57
    INGS
    2.95
     ings
    1.86
    nings
    1.60
    tings
    1.58
    ngs
    1.32
    vings
    1.27
    ppings
    1.23
    lings
    1.22
    dings
    1.18
    Activations Density 0.081%

    No Known Activations