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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 9-GEMMASCOPE-RES-16K
    6. 1488
    Prev
    Next
    INDEX
    Explanations

    phrases related to healthcare, particularly surgical procedures and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     JTextArea
    -0.65
    กระท
    -0.65
    ẢN
    -0.64
    httphttps
    -0.63
    zwungen
    -0.63
    ramienta
    -0.62
     PARSER
    -0.62
     HasFactory
    -0.61
    antart
    -0.61
     Barracks
    -0.59
    POSITIVE LOGITS
     censiti
    0.45
    yntaxException
    0.45
     appointment
    0.44
    cjon
    0.43
     trọn
    0.43
     clients
    0.42
    オール
    0.42
    ngdoc
    0.42
    PropertyGroup
    0.41
    лір
    0.41
    Activations Density 0.321%

    No Known Activations