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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 14431
    Prev
    Next
    INDEX
    Explanations

    technical instructions related to files and directories

    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
     дописавши
    -0.42
    
    -0.37
     affichés
    -0.36
    interopRequire
    -0.33
    spół
    -0.33
    HttpMethod
    -0.32
    tvguidetime
    -0.32
     Klub
    -0.32
     विश्वसनीयता
    -0.31
    ोंने
    -0.31
    POSITIVE LOGITS
     directory
    1.88
     folder
    1.87
     folders
    1.64
     directories
    1.64
     Folder
    1.52
    directory
    1.51
    folder
    1.46
    Directory
    1.41
     Directory
    1.41
    Folder
    1.38
    Activations Density 0.710%

    No Known Activations