© 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. 9005
    Prev
    Next
    INDEX
    Explanations

    phrases indicating perception or opinion

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

    Comes before "to be" or a verb

    np_acts-logits-general · gemini-2.0-flash

    seem to verb

    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
    看上去
    -0.62
     reportedly
    -0.60
     apparently
    -0.58
    看起来
    -0.56
    看起來
    -0.54
     allegedly
    -0.52
     Presumably
    -0.51
     Seem
    -0.50
     doubtless
    -0.50
     supuestamente
    -0.49
    POSITIVE LOGITS
    WithIOException
    0.87
    sizeCache
    0.85
    ReusableCell
    0.83
    MessageTagHelper
    0.76
    MLLoader
    0.75
    rungsseite
    0.75
    EDEFAULT
    0.75
    олові
    0.74
     незавершена
    0.72
    matchCondition
    0.72
    Activations Density 0.141%

    No Known Activations