© 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
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 12516
    Prev
    Next
    INDEX
    Explanations

    terms related to software licensing and redistribution rights

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

    "gen" followed by a number or period

    np_acts-logits-general · gemini-2.0-flash

    SAP

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DockStyle
    -0.66
     nonUne
    -0.63
    httphttps
    -0.58
    انجليز
    -0.50
    fjspx
    -0.48
    AnchorTagHelper
    -0.48
    ętr
    -0.47
    onicus
    -0.47
    ⇄
    -0.45
    jante
    -0.44
    POSITIVE LOGITS
     disambiguazione
    0.46
    JsonInclude
    0.45
     conozco
    0.39
    ()]);
    0.37
     żyw
    0.36
     urma
    0.36
     genoux
    0.36
     lentejuelas
    0.35
    "]);
    0.35
     okrąg
    0.35
    Activations Density 1.394%

    No Known Activations