© 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. 18-GEMMASCOPE-RES-16K
    11. 6228
    Prev
    Next
    INDEX
    Explanations

    references to mountains and their various names

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

    after "Mount" or "Mt"

    np_acts-logits-general · gemini-2.0-flash

    mountain names and locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    interopRequire
    -0.82
    новниш
    -0.72
    onoi
    -0.66
    tableFuture
    -0.59
    rzost
    -0.58
    躇
    -0.58
    getItemId
    -0.58
    onedDateTime
    -0.55
    awtextra
    -0.55
     بيها
    -0.54
    POSITIVE LOGITS
     Mount
    1.12
    Mount
    1.10
     MOUNT
    0.96
     Mounts
    0.96
     Mt
    0.94
     mounts
    0.94
    MOUNT
    0.93
     mount
    0.93
    mount
    0.89
    Mt
    0.88
    Activations Density 0.098%

    No Known Activations