© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 82561
    Prev
    Next
    INDEX
    Explanations

    substrings related to the concept of initials or initializations in programming

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

    the beginning or first instance and what follows

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للمعارف
    -0.66
     varandra
    -0.58
     chrétien
    -0.56
    enumi
    -0.54
    AddTagHelper
    -0.53
     bénévol
    -0.52
     columnIndex
    -0.49
     levier
    -0.48
     télécharge
    -0.47
     vectorielles
    -0.47
    POSITIVE LOGITS
     Initial
    1.25
     initial
    1.19
    Initial
    1.16
     INITIAL
    1.09
     Inicial
    1.08
    INITIAL
    1.07
    initial
    1.05
     initi
    0.99
    initi
    0.99
     inicial
    0.99
    Activations Density 0.023%

    No Known Activations