© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 20-GEMMASCOPE-RES-16K
    11. 14844
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to geographical locations and natural resources

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

    following "the" or "east"/"East" that refer to a coast

    np_acts-logits-general · gemini-2.0-flash

    east coast

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Bg
    -0.45
    </blockquote>
    -0.42
     ujednoznacz
    -0.41
     Bridge
    -0.40
    Bridge
    -0.39
    ***
    -0.39
    天上
    -0.38
    **
    -0.38
     mute
    -0.38
     sobre
    -0.38
    POSITIVE LOGITS
     coast
    1.80
     coasts
    1.44
     Coast
    1.37
    coast
    1.32
     coastline
    1.31
     COAST
    1.18
    Coast
    1.14
     shore
    1.12
     shores
    1.10
     shoreline
    1.01
    Activations Density 0.147%

    No Known Activations