© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 7787
    Prev
    Next
    INDEX
    Explanations

    instances of abstracts or summaries in academic contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Text containing "abstract"

    np_acts-logits-general · gemini-2.0-flash

    abstract followed by colon or description

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     setw
    -0.69
    ส์
    -0.69
    FileNotFound
    -0.68
     pouss
    -0.67
     dgv
    -0.65
    loadModel
    -0.64
     sinu
    -0.63
     Италијани
    -0.63
     Billie
    -0.62
    postmedia
    -0.62
    POSITIVE LOGITS
     abstracts
    1.16
    abstract
    1.05
     Abstracts
    1.03
    Abstracts
    1.01
    abstractmethod
    0.94
     Abstract
    0.93
    Abstract
    0.92
     abstract
    0.84
     抽象
    0.83
    abstra
    0.82
    Activations Density 0.088%

    No Known Activations