© 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-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 106157
    Prev
    Next
    INDEX
    Explanations

    geographical features and landmarks related to trails and rivers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     AssemblyCulture
    -0.52
     Utama
    -0.45
    Portale
    -0.44
     Heraus
    -0.42
    retudo
    -0.41
     Erscheinung
    -0.41
     виправивши
    -0.40
     IBOutlet
    -0.40
    UrlResolution
    -0.40
    LabelTagHelper
    -0.39
    POSITIVE LOGITS
     Bic
    0.51
    brew
    0.50
     bic
    0.50
    openConnection
    0.48
    unic
    0.48
     truncation
    0.45
    devi
    0.45
    ardi
    0.45
    ervation
    0.44
    aloo
    0.43
    Activations Density 0.026%

    No Known Activations