© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 13-GEMMASCOPE-RES-16K
    11. 7971
    Prev
    Next
    INDEX
    Explanations

    evaluative language concerning merit and fairness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WriteBarrier
    -0.51
    PreferredItem
    -0.47
     EconPapers
    -0.38
    ModelAdmin
    -0.35
    ioutil
    -0.35
    multer
    -0.35
    PostInfinity
    -0.35
    versiti
    -0.34
     LIABILITY
    -0.34
     initComponents
    -0.34
    POSITIVE LOGITS
    principalColumn
    0.53
     jadx
    0.52
    ſelf
    0.48
    ypal
    0.48
    RICS
    0.44
     postId
    0.43
    说实话
    0.43
     Kriterien
    0.43
    JO
    0.43
     ſtand
    0.43
    Activations Density 0.558%

    No Known Activations