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

    Neuronpedia

    Jacobian LensNEW
    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. 15228
    Prev
    Next
    INDEX
    Explanations

    titles and references to publications or media

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

    proper nouns and capitalized words that serve as titles or names of specific entities.

    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
     noDo
    -0.55
     للمعارف
    -0.54
     autorytatywna
    -0.46
    Enfant
    -0.45
    IntoConstraints
    -0.44
    المناصب
    -0.43
     VIDEOTAPE
    -0.43
    ruptedException
    -0.42
    存于互联网档案馆
    -0.40
     pleaſure
    -0.40
    POSITIVE LOGITS
    capes
    0.44
    trata
    0.42
    çalves
    0.41
     CreateTagHelper
    0.41
    MouseAdapter
    0.40
     Riggs
    0.39
    }],
    0.39
    cape
    0.38
     honden
    0.37
     dikel
    0.37
    Activations Density 0.690%

    No Known Activations