© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 37-GEMMASCOPE-RES-16K
    6. 5554
    Prev
    Next
    INDEX
    Explanations

    forms of the verb "to be," focusing on their various usages in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -------------</
    -0.39
     kullanılır
    -0.35
    transQ
    -0.35
    ContentAlignment
    -0.32
    ässig
    -0.31
     denotes
    -0.31
    rrggbb
    -0.31
    兼
    -0.31
    ISM
    -0.31
     tama
    -0.31
    POSITIVE LOGITS
     becoming
    1.78
    becoming
    1.45
     proving
    1.45
     getting
    1.43
     gaining
    1.34
     causing
    1.27
     growing
    1.23
     making
    1.23
     showing
    1.17
     attracting
    1.17
    Activations Density 0.513%

    No Known Activations