© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 41-GEMMASCOPE-RES-16K
    11. 4778
    Prev
    Next
    INDEX
    Explanations

    monetary values or references to financial transactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     INTERESAR
    -0.50
    KommentareTeilen
    -0.40
    onOptions
    -0.39
    脚注の使い方
    -0.37
    yarnpkg
    -0.36
    dersfield
    -0.36
    UnusedPrivate
    -0.36
    IUrlHelper
    -0.36
     فريبيس
    -0.35
    Cyfarwyddwr
    -0.35
    POSITIVE LOGITS
     sign
    3.45
     Sign
    3.11
     signing
    3.05
     SIGN
    3.00
    sign
    2.97
    Sign
    2.94
     signed
    2.91
     Signing
    2.69
    SIGN
    2.64
     signe
    2.61
    Activations Density 0.996%

    No Known Activations