© 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. 16-GEMMASCOPE-RES-16K
    11. 7869
    Prev
    Next
    INDEX
    Explanations

    phrases related to measurement and estimation processes

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

    that intensify or modify adjectives/adverbs

    np_acts-logits-general · gemini-2.0-flash

    quantifying or qualifying common words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    #+#
    -0.86
    yntaxException
    -0.77
    ValueStyle
    -0.68
    Przypisy
    -0.66
    PYX
    -0.66
     ivelany
    -0.62
    bootstrapcdn
    -0.62
    tagHelperRunner
    -0.62
    ьаж
    -0.59
    parsedMessage
    -0.58
    POSITIVE LOGITS
     pretty
    0.77
     very
    0.77
     something
    0.77
     really
    0.70
     only
    0.65
     quite
    0.63
     relatively
    0.63
     exactly
    0.60
     almost
    0.59
     truly
    0.59
    Activations Density 0.709%

    No Known Activations