© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 36-GEMMASCOPE-RES-16K
    11. 5789
    Prev
    Next
    INDEX
    Explanations

    geographical references and mountainous landscapes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    istoitu
    -0.42
    böz
    -0.42
     AssemblyCompany
    -0.41
     intStringLen
    -0.40
     subtilis
    -0.40
    HtmlAttribute
    -0.39
     pulumi
    -0.39
    hoeddwyd
    -0.38
    
    -0.38
    DECREF
    -0.38
    POSITIVE LOGITS
     mountain
    1.94
     mountains
    1.93
     Mountains
    1.66
    mountain
    1.65
    mountains
    1.63
    Mountains
    1.55
     Mountain
    1.53
     mountainous
    1.52
    Mountain
    1.49
     MOUNTAIN
    1.41
    Activations Density 0.346%

    No Known Activations