© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 3070
    Prev
    Next
    INDEX
    Explanations

    whitespace or blank spaces in text

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

    Code, URLs, or filenames

    np_acts-logits-general · gemini-2.0-flash

    foreign and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tanleria
    -0.43
    ----</
    -0.41
     UIApplication
    -0.40
    offsetWidth
    -0.38
    UIApplication
    -0.36
    AddWithValue
    -0.36
     {}));
    -0.35
    もら
    -0.34
    忑
    -0.33
     CL
    -0.32
    POSITIVE LOGITS
     AssemblyTitle
    0.56
    Vidite
    0.56
    MessageTagHelper
    0.54
     ProtoMessage
    0.47
    Rujuakan
    0.45
     klart
    0.45
     AssemblyCompany
    0.44
     indivíduo
    0.44
    struktion
    0.44
     Económica
    0.44
    Activations Density 0.338%

    No Known Activations