© 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. 5719
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the existence or characteristics of medical devices or technologies

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

    Passive voice, describing something being done or made

    np_acts-logits-general · gemini-2.0-flash

    defined by composition or function

    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
     Putting
    -0.59
     happening
    -0.58
    Putting
    -0.54
    Giving
    -0.53
     passando
    -0.52
     going
    -0.52
     GOING
    -0.52
     Taking
    -0.51
     dando
    -0.50
     Giving
    -0.50
    POSITIVE LOGITS
     characterized
    1.09
     characterised
    1.02
     composed
    0.97
     based
    0.89
    tagHelperRunner
    0.87
     constructed
    0.86
     divided
    0.86
     designed
    0.84
     governed
    0.83
     protoimpl
    0.83
    Activations Density 1.021%

    No Known Activations