© 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
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 106148
    Prev
    Next
    INDEX
    Explanations

    mentions of helper functions or tools in the context of programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AnchorStyles
    -0.54
    UIControlState
    -0.50
    AndroidJUnit
    -0.50
    VideoCapture
    -0.49
    Xna
    -0.47
    TemporalType
    -0.46
    󠁮
    -0.45
    MessageState
    -0.44
     doInBackground
    -0.44
     MacMillan
    -0.43
    POSITIVE LOGITS
     Helper
    1.41
    Helper
    1.39
     helper
    1.33
    helper
    1.26
     Helpers
    1.19
     helpers
    1.17
    Helpers
    1.06
    helpers
    1.01
    helping
    0.84
     Helps
    0.81
    Activations Density 0.005%

    No Known Activations