© 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. 14-GEMMASCOPE-RES-16K
    6. 2443
    Prev
    Next
    INDEX
    Explanations

    specific biological or medical terminologies and their contextual use in various texts

    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
     AssemblyCulture
    -1.19
     Rasp
    -1.17
    存于互联网档案馆
    -1.16
    Manbalar
    -1.13
    makeConstraints
    -1.10
     CreateTagHelper
    -1.09
     configureStore
    -1.05
    onAttach
    -1.05
    fördert
    -1.05
    haustible
    -1.05
    POSITIVE LOGITS
    y
    1.74
    o
    1.67
    a
    1.21
    i
    1.18
    er
    1.17
    ه
    1.15
    t
    1.14
    e
    1.13
    yny
    1.12
    en
    1.02
    Activations Density 1.607%

    No Known Activations