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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 13-GEMMASCOPE-RES-16K
    6. 4378
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to drug efficacy and patient responses to medications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     circonst
    -0.48
    reszcie
    -0.47
    ccione
    -0.47
    ksz
    -0.46
    姉妹
    -0.44
     embarrassment
    -0.43
    AppMethodBeat
    -0.43
    zel
    -0.41
     ISNI
    -0.41
     honte
    -0.41
    POSITIVE LOGITS
    EndTag
    0.61
     differently
    0.61
    iosync
    0.60
     createStore
    0.57
     Houſe
    0.56
     bParam
    0.55
     processes
    0.54
     vPvB
    0.53
     behave
    0.53
     behaved
    0.53
    Activations Density 0.507%

    No Known Activations