© 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. 15-GEMMASCOPE-RES-16K
    11. 2271
    Prev
    Next
    INDEX
    Explanations

    syntax related to file handling and package management in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RTLR
    -0.31
    前
    -0.31
     Lieben
    -0.28
    Bibliographie
    -0.28
     before
    -0.28
    抜
    -0.28
     off
    -0.27
    苓
    -0.27
     antes
    -0.27
     rock
    -0.26
    POSITIVE LOGITS
    DATABASES
    0.68
    EndGlobalSection
    0.65
    AnchorStyles
    0.63
     queſta
    0.60
    DispatchToProps
    0.59
    省市镇
    0.59
    awtextra
    0.59
     LinkedHashMap
    0.58
     TreeMap
    0.57
    Jeografia
    0.56
    Activations Density 0.558%

    No Known Activations