© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 460
    Prev
    Next
    INDEX
    Explanations

    descriptive phrases about geographical features and landscapes

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

    geographical features and landmarks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     JpaRepository
    -0.64
     comis
    -0.57
    UnknownFieldSet
    -0.52
     సౌకర్య
    -0.49
    weiser
    -0.49
    resave
    -0.48
     flüs
    -0.48
    testens
    -0.48
    InjectMocks
    -0.48
    Ширина
    -0.47
    POSITIVE LOGITS
     mountain
    0.97
     hill
    0.96
     mountains
    0.94
     hills
    0.94
     peaks
    0.87
     peak
    0.81
     escarp
    0.78
     ridge
    0.76
     moun
    0.76
    mountains
    0.76
    Activations Density 0.294%

    No Known Activations