Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 5718
    Prev
    Next
    INDEX
    Explanations

    functions and methods related to getting and retrieving data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     newNode
    -0.68
     onClose
    -0.68
     deleteById
    -0.66
     companyId
    -0.66
    SBATCH
    -0.63
     accountId
    -0.60
     columnIndex
    -0.60
     randomNumber
    -0.59
     AssemblyCompany
    -0.59
    MessageTagHelper
    -0.59
    POSITIVE LOGITS
    get
    1.20
    Get
    1.04
     get
    1.00
     Get
    0.96
    GET
    0.90
     GET
    0.84
     gets
    0.73
     Getter
    0.73
    Gets
    0.72
     Gets
    0.70
    Activations Density 0.062%

    No Known Activations