Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 12800
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific measurements and results

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

    Follows "the," "we," or a comma

    np_acts-logits-general · gemini-2.0-flash

    ascension and improvements

    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
     unsuitable
    -0.67
     unfit
    -0.63
     dysfunctional
    -0.58
     nightmares
    -0.55
     Worst
    -0.54
     nightmare
    -0.54
    worst
    -0.54
     troublesome
    -0.53
     incomplete
    -0.53
     forbidding
    -0.52
    POSITIVE LOGITS
     successes
    1.13
     positive
    1.09
     success
    1.01
     triumphant
    1.00
     victories
    0.97
     triumphs
    0.95
    Positive
    0.94
     triumph
    0.94
     praise
    0.93
     Positive
    0.93
    Activations Density 0.983%

    No Known Activations