© 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. 11245
    Prev
    Next
    INDEX
    Explanations

    technical terms related to vector mathematics and programming structures

    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
     Szen
    -0.35
    Géographie
    -0.35
    vision
    -0.33
     patron
    -0.31
    anian
    -0.30
    Bra
    -0.30
    ņa
    -0.29
     tendances
    -0.29
    Vision
    -0.29
    χρι
    -0.29
    POSITIVE LOGITS
     vertices
    0.87
     vertex
    0.79
     Vertex
    0.73
    expandindo
    0.71
     normals
    0.69
     VERT
    0.64
     CreateTagHelper
    0.63
    vertex
    0.63
     UV
    0.60
    IVer
    0.60
    Activations Density 0.157%

    No Known Activations