© 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. 22-GEMMASCOPE-RES-16K
    6. 11439
    Prev
    Next
    INDEX
    Explanations

    references to geographical features and locations

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

    Land formations: hills, mountains, ridges

    np_acts-logits-general · gemini-2.0-flash

    elevated landforms and points

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tvguidetime
    -0.72
    CppCodeGen
    -0.59
     overcrow
    -0.55
    Parcelize
    -0.54
     CommonModule
    -0.52
     FetchType
    -0.52
    InjectMocks
    -0.51
    出版年
    -0.51
     Türen
    -0.49
     nakalista
    -0.49
    POSITIVE LOGITS
     hill
    1.44
     hills
    1.28
     hillside
    1.13
     ridge
    1.09
     mountain
    1.08
     cliff
    1.00
     steep
    1.00
     hilly
    0.99
     ridges
    0.99
    hill
    0.99
    Activations Density 0.203%

    No Known Activations