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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 9862
    Prev
    Next
    INDEX
    Explanations

    elements related to categories, varieties, and classifications of offerings or options

    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
    👈
    -0.36
     folgte
    -0.35
    ніципалі
    -0.35
    viewDid
    -0.34
     quitté
    -0.33
     live
    -0.33
     pozw
    -0.33
    서는
    -0.33
     lebte
    -0.32
    (&:
    -0.32
    POSITIVE LOGITS
     ffilmiau
    0.66
     including
    0.65
     <=",
    0.63
    abestanden
    0.63
    IsContent
    0.59
     ujednoznacz
    0.58
     kuten
    0.58
     such
    0.57
     CreateTagHelper
    0.56
     yaitu
    0.55
    Activations Density 0.477%

    No Known Activations