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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 9630
    Prev
    Next
    INDEX
    Explanations

    conversational phrases often used at the beginning of sentences

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

    "Well" followed by a comma or conversational continuation

    np_acts-logits-general · gemini-2.0-flash

    starts with well

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dist
    -0.36
      
    -0.33
     Co
    -0.32
    dist
    -0.32
    ci
    -0.31
    ↵↵↵
    -0.31
    ↵↵
    -0.30
    客様
    -0.30
    ся
    -0.30
    香
    -0.30
    POSITIVE LOGITS
     Infór
    0.64
     imagui
    0.63
     viewDidLoad
    0.63
     Administrativna
    0.63
    principalColumn
    0.62
     utafitiHapana
    0.62
    EDEFAULT
    0.60
     beſte
    0.60
     ſind
    0.60
    niſſe
    0.60
    Activations Density 0.065%

    No Known Activations