© 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. 21-GEMMASCOPE-RES-16K
    6. 14477
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to software programming and configuration management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     initComponents
    -0.91
     otomatig
    -0.78
    StructEnd
    -0.73
     المعيارى
    -0.69
    PickerController
    -0.66
    kháu
    -0.65
    AndEndTag
    -0.65
    PreferredItem
    -0.65
    :+:
    -0.64
    tagHelperRunner
    -0.63
    POSITIVE LOGITS
    izes
    0.62
    KURZBESCHREIBUNG
    0.53
    kuje
    0.48
    calfe
    0.47
    lizes
    0.46
    cribes
    0.45
     Does
    0.45
    Does
    0.44
    gives
    0.44
     does
    0.44
    Activations Density 0.044%

    No Known Activations