© 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. 4422
    Prev
    Next
    INDEX
    Explanations

    discussions about collaboration and teamwork

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

    "work" or "working"

    np_acts-logits-general · gemini-2.0-flash

    work with or toward

    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
     spazz
    -0.28
     montant
    -0.27
    responsibility
    -0.26
    rrggbb
    -0.25
    vetica
    -0.25
    फी
    -0.25
    posób
    -0.24
    czas
    -0.24
     responsabilité
    -0.24
     pri
    -0.24
    POSITIVE LOGITS
    Worked
    0.69
     tirelessly
    0.67
    ValueStyle
    0.66
    hopped
    0.65
     Worked
    0.64
    Tikang
    0.64
     CreateTagHelper
    0.63
     harder
    0.61
    worked
    0.60
     collaboratively
    0.59
    Activations Density 0.107%

    No Known Activations