Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 5703
    Prev
    Next
    INDEX
    Explanations

    phrases related to the action of adding something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     IActionResult
    -0.58
    viewController
    -0.51
    APIView
    -0.49
    értel
    -0.48
     Schaefer
    -0.46
    currentTime
    -0.46
    IActionResult
    -0.46
                                   
    -0.45
    reinterpret
    -0.45
     UnityEngine
    -0.45
    POSITIVE LOGITS
     add
    1.09
     Add
    1.09
    Add
    1.02
    add
    1.02
     added
    1.01
     adds
    0.99
     additions
    0.98
     addition
    0.98
    added
    0.98
     Adds
    0.98
    Activations Density 0.094%

    No Known Activations