© 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. 16-GEMMASCOPE-RES-16K
    6. 13340
    Prev
    Next
    INDEX
    Explanations

    descriptive phrases related to living spaces and their features

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

    Preceding specific words ("requirement", "parents", "above")

    np_acts-logits-general · gemini-2.0-flash

    an arched requirement to the parents

    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
    UserScript
    -0.66
    BorderLayout
    -0.62
     صوتيه
    -0.61
     doInBackground
    -0.60
    BeginContext
    -0.59
    таратура
    -0.59
    RTLI
    -0.58
    AutoField
    -0.58
     MediatR
    -0.57
     protoimpl
    -0.57
    POSITIVE LOGITS
     kasarigan
    0.59
    WebElementEntity
    0.50
    aucune
    0.43
     ebenfalls
    0.43
     esso
    0.41
     accessed
    0.41
     nicely
    0.41
    Nicely
    0.41
    ाष
    0.41
    Искәрмәләр
    0.40
    Activations Density 0.026%

    No Known Activations