© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 3305
    Prev
    Next
    INDEX
    Explanations

    instances of the word "grant" and its variations, indicating a focus on funding or permission-related contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     déb
    -0.48
     usah
    -0.44
     Dues
    -0.39
     fairly
    -0.38
     белье
    -0.37
    ellen
    -0.37
     profession
    -0.36
    ề
    -0.36
    WebElementEntity
    -0.35
     fallu
    -0.35
    POSITIVE LOGITS
     granted
    1.05
     grant
    1.05
     grants
    1.00
    granted
    0.96
    grant
    0.96
    grants
    0.92
    Grant
    0.92
    Grants
    0.88
     Grant
    0.87
     GRANT
    0.87
    Activations Density 0.119%

    No Known Activations