© 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. 63262
    Prev
    Next
    INDEX
    Explanations

    questions and themes related to understanding risks, implications, and differences in various contexts

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

    asking about implications and meaning

    np_acts-logits-general · gemini-2.5-flash-lite

    questions that seek interpretation, purpose, implications (including risks/benefits), or instructions on how something should be used.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
    LookAnd
    -0.71
    GraphicsUnit
    -0.70
     AssemblyCompany
    -0.65
    contentLoaded
    -0.60
    AISSEE
    -0.57
     Мексичка
    -0.55
     AssemblyProduct
    -0.54
     defaultstate
    -0.54
    DrawerToggle
    -0.54
     незавершена
    -0.52
    POSITIVE LOGITS
    IntoConstraints
    0.48
    AxisAlignment
    0.40
    LayoutConstraint
    0.37
    })));
    0.36
    chera
    0.36
     Multi
    0.36
    توض
    0.35
    يميديا
    0.34
    AccessorTable
    0.34
    Anim
    0.34
    Activations Density 0.513%

    No Known Activations