© 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. 2-GEMMASCOPE-RES-16K
    6. 8929
    Prev
    Next
    INDEX
    Explanations

    specific technical terms and identifiers related to programming or APIs

    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
    APOLIS
    -0.54
    ]")]
    -0.49
    Tracce
    -0.46
    Vidite
    -0.46
    ials
    -0.45
    SuppressLint
    -0.45
    InputBorder
    -0.45
    LogFactory
    -0.45
    disclosure
    -0.45
    धार
    -0.44
    POSITIVE LOGITS
    ite
    1.68
    it
    1.65
    ites
    1.61
    ITE
    1.51
    IT
    1.44
    its
    1.38
    ita
    1.36
    ited
    1.30
    ITS
    1.29
    ITES
    1.26
    Activations Density 2.055%

    No Known Activations