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. 12890
    Prev
    Next
    INDEX
    Explanations

    usages and impacts of medical treatments and their side effects

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

    a return or relapse

    np_acts-logits-general · gemini-2.0-flash

    revert or return

    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
     onResponse
    -0.52
    rauch
    -0.52
     einde
    -0.50
     contemplates
    -0.49
    hydrate
    -0.48
     contemplate
    -0.47
    Ikus
    -0.46
     füllen
    -0.45
     Foote
    -0.45
     endlich
    -0.45
    POSITIVE LOGITS
     reverted
    1.07
     reverting
    1.07
     revert
    1.00
     reinst
    0.95
     reversion
    0.91
    revert
    0.90
     wieder
    0.84
     다시
    0.83
     novamente
    0.83
     again
    0.83
    Activations Density 0.415%

    No Known Activations