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. 28-GEMMASCOPE-RES-16K
    6. 4269
    Prev
    Next
    INDEX
    Explanations

    terms related to school events and scheduling details

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

    Resumption, reduction, or removal of restrictions

    np_acts-logits-general · gemini-2.0-flash

    restrictions and their easing

    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
     تضيفلها
    -0.51
    httphttps
    -0.40
     REF
    -0.36
    zzati
    -0.36
     Vork
    -0.34
     Silber
    -0.34
    krom
    -0.33
    character
    -0.33
     استنادى
    -0.32
     EconPapers
    -0.32
    POSITIVE LOGITS
     restrictions
    0.82
     easing
    0.70
     Restrictions
    0.70
    restrictions
    0.69
     restriction
    0.69
     curfew
    0.67
     pleaſure
    0.61
     reopening
    0.60
    Restrictions
    0.60
     Restriction
    0.60
    Activations Density 0.067%

    No Known Activations