© 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. 15-GEMMASCOPE-RES-16K
    6. 1903
    Prev
    Next
    INDEX
    Explanations

    specific numerical data and their relationships in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    principalColumn
    -0.53
    AccessorTable
    -0.51
    AutoScaleMode
    -0.49
     iprot
    -0.48
     ujednoznacz
    -0.45
    quit
    -0.44
     ReactDOM
    -0.44
    impulse
    -0.43
    expandindo
    -0.43
    /**
    -0.43
    POSITIVE LOGITS
     chocs
    0.38
    InputTagHelper
    0.37
    httphttps
    0.37
    acamata
    0.36
    backen
    0.36
    StoreMessageInfo
    0.36
    Including
    0.36
     incluida
    0.35
     contando
    0.34
     Jumat
    0.34
    Activations Density 0.958%

    No Known Activations