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

    Neuronpedia

    Jacobian LensNEW
    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. 14-GEMMASCOPE-RES-16K
    11. 13958
    Prev
    Next
    INDEX
    Explanations

    the section headings for abstracts in academic papers

    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
     Henson
    -0.72
     pouss
    -0.68
    QApplication
    -0.67
     dgv
    -0.67
    Nino
    -0.65
    RunWith
    -0.63
    loadModel
    -0.63
    FileNotFound
    -0.63
    CultureInfo
    -0.63
    lež
    -0.63
    POSITIVE LOGITS
     abstracts
    1.34
    abstract
    1.23
     Abstract
    1.14
    Abstract
    1.14
     Abstracts
    1.13
     abstract
    1.10
    abstractmethod
    1.09
     ABSTRACT
    1.03
    Abstracts
    0.98
     abstracto
    0.97
    Activations Density 0.117%

    No Known Activations