© 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. 54240
    Prev
    Next
    INDEX
    Explanations

    references to models and their specifications

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

    archaic or non-english words

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

    the token "model" (occurrences of the word "model", often as a speaker/label token).

    oai_token-act-pair · gpt-5-miniTriggered 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
     Италијани
    -0.44
     written
    -0.41
     pyplot
    -0.37
    PutMapping
    -0.37
    AutoField
    -0.37
    statechange
    -0.37
     Chwiliwch
    -0.37
    CardModule
    -0.36
     surla
    -0.36
    طلحات
    -0.36
    POSITIVE LOGITS
    principalColumn
    0.57
     humains
    0.53
     répon
    0.52
     purpoſe
    0.52
     utafitiHapana
    0.50
    NUMX
    0.50
    GOTREF
    0.50
     civilización
    0.50
     avoient
    0.49
     fhew
    0.49
    Activations Density 0.001%

    No Known Activations