© 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-2-9B
    4. Residual Stream - 16k
    5. 27-GEMMASCOPE-RES-16K
    6. 10014
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to significant events and announcements, particularly in a global or political context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    getragen
    -0.45
    tagHelperRunner
    -0.43
     dermed
    -0.38
     Verhält
    -0.38
     guantes
    -0.38
     zís
    -0.38
     convidados
    -0.38
     forhold
    -0.37
     disfraces
    -0.37
     disambiguazione
    -0.37
    POSITIVE LOGITS
     FTX
    0.57
     ChatGPT
    0.56
     <=",
    0.55
     StatelessWidget
    0.55
     Brexit
    0.55
     hurricanes
    0.54
     lockdowns
    0.54
    CodedInputStream
    0.53
    arakhand
    0.53
     COVID
    0.53
    Activations Density 0.729%

    No Known Activations