© 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. 5356
    Prev
    Next
    INDEX
    Explanations

    terms related to categories and confirmations in a digital context

    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
    Hochspringen
    -0.29
     cucchia
    -0.28
     aufzu
    -0.28
    شرين
    -0.26
     εκεί
    -0.26
     justamente
    -0.25
     fidanz
    -0.25
     AspNetCore
    -0.24
     geweest
    -0.24
     versehen
    -0.24
    POSITIVE LOGITS
    ländische
    0.67
    AddTagHelper
    0.66
     internetowa
    0.64
    ConstraintMaker
    0.61
    ový
    0.60
    jąca
    0.60
    ництво
    0.59
    графія
    0.59
    льная
    0.58
    Personensuche
    0.57
    Activations Density 0.076%

    No Known Activations