© 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. 9231
    Prev
    Next
    INDEX
    Explanations

    terms related to misrepresentation or misunderstandings

    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
     שוליים
    -0.93
     חיצוניים
    -0.92
    ContentAsync
    -0.85
    InjectMocks
    -0.83
    sizeCache
    -0.83
     LCCN
    -0.79
    expandindo
    -0.78
    LabelTagHelper
    -0.77
    tagHelperRunner
    -0.77
    AccessorTable
    -0.76
    POSITIVE LOGITS
     mis
    3.77
     Mis
    3.29
    Mis
    3.26
    mis
    3.08
     MIS
    2.65
    MIS
    2.43
     misread
    1.60
     mismatch
    1.53
     miscon
    1.52
     mise
    1.51
    Activations Density 0.038%

    No Known Activations