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. 13-GEMMASCOPE-RES-16K
    6. 7086
    Prev
    Next
    INDEX
    Explanations

    phrases concerning success, quality, and personal opinion

    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
     Gau
    -0.40
    folger
    -0.39
    webElementXpaths
    -0.38
    EST
    -0.38
    autoreleasepool
    -0.36
    enskap
    -0.36
    Française
    -0.36
    HomeAsUpEnabled
    -0.36
     ANT
    -0.36
     lej
    -0.35
    POSITIVE LOGITS
     للاسماء
    0.55
     utafitiHapana
    0.54
    FormTagHelper
    0.47
     étoient
    0.47
    httphttps
    0.46
     vidéos
    0.46
     desmotivaciones
    0.45
     Infór
    0.45
     rocas
    0.44
     feroit
    0.43
    Activations Density 0.668%

    No Known Activations