© 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. 33-GEMMASCOPE-RES-16K
    11. 602
    Prev
    Next
    INDEX
    Explanations

    specific names or labels related to cultural, geographical, and scientific terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -0.39
    vraagd
    -0.38
    }{*}{}
    -0.37
     Sinus
    -0.37
    ástica
    -0.37
     AssemblyCompany
    -0.35
     serrated
    -0.35
     Cinque
    -0.35
    letoe
    -0.34
    pédie
    -0.34
    POSITIVE LOGITS
    ian
    1.32
    IAN
    1.23
    lian
    1.09
    ians
    1.08
    tian
    1.07
    cian
    1.04
     ian
    1.00
    sian
    0.99
    vian
    0.99
    rian
    0.96
    Activations Density 0.291%

    No Known Activations