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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 21747
    Prev
    Next
    INDEX
    Explanations

    elements related to accidents and traffic incidents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     propOrder
    -0.80
    CppMethod
    -0.65
    +#+#
    -0.60
    RTCK
    -0.59
     EconPapers
    -0.55
    ########.
    -0.54
    RTEX
    -0.53
    internalType
    -0.52
    ppur
    -0.50
    tagHelperRunner
    -0.50
    POSITIVE LOGITS
     traffic
    0.41
    PyExc
    0.36
    HtmlAttribute
    0.36
     cars
    0.35
     vehic
    0.35
     recibo
    0.32
     dueño
    0.31
     traff
    0.30
     automobiles
    0.30
    WriteTagHelper
    0.30
    Activations Density 0.012%

    No Known Activations