© 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. 31-GEMMASCOPE-RES-16K
    11. 4572
    Prev
    Next
    INDEX
    Explanations

    phrases indicating conditions or requirements related to a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the phrase "as well as" used to list additional items or expand on previous statements.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     EconPapers
    -0.59
     NgModule
    -0.52
    transQ
    -0.48
    ########.
    -0.48
     _('
    -0.46
    Abit
    -0.45
     onBackPressed
    -0.45
    DeleteBehavior
    -0.44
     useDispatch
    -0.44
    glfw
    -0.42
    POSITIVE LOGITS
     thereby
    0.62
     presumably
    0.53
     denen
    0.50
    awtextra
    0.49
    SharedCtor
    0.48
    それも
    0.45
     cioè
    0.45
     hence
    0.45
    즉
    0.43
    etheless
    0.43
    Activations Density 1.588%

    No Known Activations