© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 14-GEMMASCOPE-RES-16K
    6. 9383
    Prev
    Next
    INDEX
    Explanations

    specific terms related to medical conditions and treatments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/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.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kaarangay
    -0.55
    Autoritní
    -0.52
     Verbrauch
    -0.51
     primul
    -0.49
     Савезне
    -0.49
     szint
    -0.48
    WireFormatLite
    -0.47
     Shoulders
    -0.47
     délic
    -0.47
     zák
    -0.47
    POSITIVE LOGITS
    URLException
    0.69
     GenerationType
    0.69
    Diweddarwch
    0.67
     InputDecoration
    0.63
     utafitiHapana
    0.62
     նաև
    0.58
    bewerken
    0.57
     BNF
    0.57
    tagHelperRunner
    0.57
    XtraBars
    0.55
    Activations Density 0.883%

    No Known Activations