© 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. 35-GEMMASCOPE-RES-16K
    11. 8384
    Prev
    Next
    INDEX
    Explanations

    code-related syntax and keywords, particularly those associated with object manipulation and conditional statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/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.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rungsseite
    -0.80
     AssemblyCulture
    -0.79
    Personendaten
    -0.66
    >",
    -0.66
    %"),
    -0.64
    addCriterion
    -0.64
    出版年
    -0.62
     autorytatywna
    -0.61
     CreateTagHelper
    -0.60
     queſta
    -0.59
    POSITIVE LOGITS
     imprensa
    0.40
     totul
    0.39
    írus
    0.39
    UpInside
    0.39
    PointSize
    0.39
    ↵↵↵
    0.38
    ↵↵
    0.37
     daarvan
    0.37
    Together
    0.36
     tadi
    0.36
    Activations Density 0.479%

    No Known Activations