© 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. 20-GEMMASCOPE-RES-131K
    11. 53531
    Prev
    Next
    INDEX
    Explanations

    programming-related expressions and structures such as conditions and method calls

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

    we select

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     snippetHide
    -0.75
    kháu
    -0.64
    AddTagHelper
    -0.64
    Datuak
    -0.63
     Audiodateien
    -0.62
    OGND
    -0.62
    contentLoaded
    -0.62
    principalTable
    -0.61
    Vidite
    -0.60
     queſta
    -0.60
    POSITIVE LOGITS
     or
    0.34
     (
    0.32
    BitConverter
    0.32
     safety
    0.31
     refuse
    0.31
     Q
    0.31
    DIPSETTING
    0.30
     free
    0.30
     Fre
    0.30
     decrease
    0.30
    Activations Density 0.050%

    No Known Activations