© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 12460
    Prev
    Next
    INDEX
    Explanations

    instances of the word 'model' and its variations in technical or programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "model"

    np_acts-logits-general · gemini-2.0-flash

    model or models

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dintre
    -0.47
    Garlic
    -0.43
    igreja
    -0.43
    comcast
    -0.43
    Percentage
    -0.42
     Anthony
    -0.42
     primeira
    -0.41
     intercamb
    -0.41
     Electricity
    -0.41
     частности
    -0.41
    POSITIVE LOGITS
     Model
    1.10
     model
    1.07
     getModel
    1.03
     ExecuteAsync
    1.02
    model
    1.01
     MODEL
    1.01
    Model
    1.00
    modelBuilder
    0.89
     Models
    0.88
    MODEL
    0.88
    Activations Density 0.077%

    No Known Activations