© 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. 9047
    Prev
    Next
    INDEX
    Explanations

    specific locations and navigational directions

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

    Road directions involving turns or exits

    np_acts-logits-general · gemini-2.0-flash

    turning or exiting

    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
    featureID
    -0.64
    WireFormat
    -0.56
    цездатний
    -0.56
    CPtr
    -0.56
    Rujuakan
    -0.56
    aarrggbb
    -0.56
     AssemblyTitle
    -0.56
    writerow
    -0.55
    ORAGE
    -0.55
    Попис
    -0.54
    POSITIVE LOGITS
     exit
    0.94
     turn
    0.92
    turn
    0.83
    Exit
    0.81
     Exit
    0.80
     exits
    0.80
     exiting
    0.79
     turning
    0.76
    Turn
    0.75
    exit
    0.74
    Activations Density 0.143%

    No Known Activations