© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 4460
    Prev
    Next
    INDEX
    Explanations

    phrases indicating an action or direction involving movement or change

    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
    #+#
    -0.80
    TagMode
    -0.79
    CppMethod
    -0.78
    :+:
    -0.73
    OGND
    -0.69
    __*/
    -0.63
    inns
    -0.61
     Zola
    -0.58
     Numa
    -0.57
    AddField
    -0.56
    POSITIVE LOGITS
    eseorang
    0.70
    quelize
    0.58
     JAXBElement
    0.50
    Extinguishing
    0.50
    PyTuple
    0.49
    entown
    0.49
    AsUp
    0.47
    InjectAttribute
    0.46
    mybatisplus
    0.46
    ngOnInit
    0.46
    Activations Density 0.637%

    No Known Activations