© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 7733
    Prev
    Next
    INDEX
    Explanations

    references to boxes and packaging

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

    "box" or "boxes."

    np_acts-logits-general · gemini-2.0-flash

    box, crate, container

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Aust
    -0.46
    stylers
    -0.44
    anasia
    -0.40
    GeneratedValue
    -0.39
     Nj
    -0.39
    ‍♂️
    -0.38
    ATURES
    -0.36
    ‍♀️
    -0.36
    glVertex
    -0.36
     Prosper
    -0.36
    POSITIVE LOGITS
     box
    1.06
     Box
    0.99
     BOX
    0.93
    Box
    0.85
    box
    0.84
     boxes
    0.84
     Boxes
    0.84
    Boxes
    0.79
    BOX
    0.78
     boxed
    0.71
    Activations Density 0.498%

    No Known Activations