© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 4019
    Prev
    Next
    INDEX
    Explanations

    words related to functionality or attributes described as 'able'

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

    ending in "-able" or "-ible"

    np_acts-logits-general · gemini-2.0-flash

    words ending in able or ible

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     Inscrivez
    -0.50
     strøm
    -0.49
    rungsseite
    -0.49
    ing
    -0.48
    ekš
    -0.47
     TÉCN
    -0.47
     ups
    -0.46
    gangss
    -0.45
     match
    -0.44
    ffions
    -0.44
    POSITIVE LOGITS
    illable
    0.86
    vable
    0.85
    ctable
    0.82
    ggable
    0.81
    entable
    0.80
    izable
    0.79
    atable
    0.78
    ortable
    0.77
    ible
    0.77
    chable
    0.77
    Activations Density 0.345%

    No Known Activations