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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 14-GEMMASCOPE-RES-16K
    6. 229
    Prev
    Next
    INDEX
    Explanations

    scientific terms related to gene expression and regulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Tembelea
    -0.77
    stateProvider
    -0.73
    
    -0.73
    #+#
    -0.71
    +#+#
    -0.70
    RRect
    -0.69
    NOPQRST
    -0.65
    AsUp
    -0.64
    </caption>
    -0.63
    fromnode
    -0.62
    POSITIVE LOGITS
     UIApplication
    0.51
    پرس
    0.48
    通用
    0.45
    ɕ
    0.44
    perform
    0.44
     mû
    0.43
     genes
    0.43
    def
    0.42
    strijd
    0.41
     générale
    0.41
    Activations Density 1.490%

    No Known Activations