© 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-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 10326
    Prev
    Next
    INDEX
    Explanations

    terms related to layers and linings in biological or structural contexts

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

    "line" or "lining"

    np_acts-logits-general · gemini-2.0-flash

    line, liner, lining, lined

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WaitGroup
    -0.48
    oneofs
    -0.47
    awtextra
    -0.45
    ніципа
    -0.45
    omock
    -0.44
    |()
    -0.43
    ſelves
    -0.42
    tikzpicture
    -0.42
     porcentual
    -0.42
    rrggbb
    -0.42
    POSITIVE LOGITS
     lining
    1.26
     Lining
    1.16
     lined
    1.02
     linings
    0.99
     Lined
    0.94
     liner
    0.84
     Liner
    0.82
    lined
    0.79
    lining
    0.78
     liners
    0.73
    Activations Density 0.224%

    No Known Activations