© 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-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 3049
    Prev
    Next
    INDEX
    Explanations

    phrases related to support systems and community assistance

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

    following "support"

    np_acts-logits-general · gemini-2.0-flash

    support structures and systems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للمعارف
    -0.81
    support
    -0.79
    SharedDtor
    -0.77
    ValueStyle
    -0.71
    Supporting
    -0.71
    .*")]
    -0.70
    ukone
    -0.70
    Support
    -0.70
     Support
    -0.69
     supporting
    -0.69
    POSITIVE LOGITS
    fully
    0.58
    IVE
    0.57
     groups
    0.56
     penuh
    0.55
     structures
    0.55
     structure
    0.53
     staff
    0.52
    orul
    0.51
     systems
    0.51
    groups
    0.50
    Activations Density 0.127%

    No Known Activations