© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 6020
    Prev
    Next
    INDEX
    Explanations

    specific locations and terminologies related to scientific concepts and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Britannique
    -0.44
     Asians
    -0.39
     celos
    -0.39
     Hügel
    -0.38
     schemes
    -0.38
     patients
    -0.38
    SCHEME
    -0.38
     panels
    -0.38
     backgrounds
    -0.37
     panneau
    -0.36
    POSITIVE LOGITS
    xi
    0.84
     يتيمه
    0.71
    XI
    0.66
    navbar
    0.64
    TagMode
    0.63
    OGND
    0.59
     xi
    0.58
    xiu
    0.58
     ujednoznacz
    0.58
    vi
    0.56
    Activations Density 1.433%

    No Known Activations