© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 33-GEMMASCOPE-RES-16K
    6. 11966
    Prev
    Next
    INDEX
    Explanations

    geometric shapes and their properties in relation to spatial arrangements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    posedge
    -0.36
     puestos
    -0.36
     miejs
    -0.34
     Tiefen
    -0.33
     Schlag
    -0.33
     Friedhof
    -0.32
     Ortsteil
    -0.32
    кість
    -0.32
    mögen
    -0.32
     πλη
    -0.31
    POSITIVE LOGITS
     square
    1.69
     rectangular
    1.68
     rectangle
    1.66
     circular
    1.52
     triangular
    1.43
     circle
    1.43
     cylindrical
    1.43
     round
    1.38
     triangle
    1.38
     Rectangular
    1.37
    Activations Density 1.281%

    No Known Activations