© 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. 23-GEMMASCOPE-RES-16K
    11. 2110
    Prev
    Next
    INDEX
    Explanations

    technical and quantitative terms related to scientific and mathematical analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Numerade
    -0.51
     Wikiseite
    -0.45
     repuesto
    -0.44
    adeloupe
    -0.43
    HttpResponse
    -0.43
     allAfrica
    -0.42
    lares
    -0.41
    
    -0.40
    redient
    -0.40
     swallow
    -0.40
    POSITIVE LOGITS
     depends
    0.64
     varies
    0.57
     zależy
    0.52
     depend
    0.51
     dépend
    0.50
     зависит
    0.49
     depende
    0.48
     dipende
    0.47
    depends
    0.47
     depender
    0.46
    Activations Density 1.180%

    No Known Activations