© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 15872
    Prev
    Next
    INDEX
    Explanations

    elements related to film, photography, and artistic production

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    窝
    -0.54
    FormBorderStyle
    -0.52
    aguya
    -0.51
    Datuak
    -0.51
    ίου
    -0.50
     설명
    -0.49
     encan
    -0.48
    kema
    -0.48
    InitStruct
    -0.48
    ':
    
    -0.47
    POSITIVE LOGITS
    SourceChecksum
    0.66
     Réalisation
    0.65
    WithIOException
    0.60
    cèse
    0.57
    farwyddwr
    0.57
    WriteTagHelper
    0.56
    CWE
    0.55
    PCell
    0.55
    Scénario
    0.54
    الإنجليزية
    0.53
    Activations Density 0.291%

    No Known Activations