© 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. 9-GEMMASCOPE-RES-16K
    11. 9473
    Prev
    Next
    INDEX
    Explanations

    concepts related to the legal system and analysis of societal issues within a historical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 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
     سكانية
    -0.58
    copg
    -0.44
     ***!
    -0.41
    ENEFITS
    -0.39
     kids
    -0.39
    ueuse
    -0.38
     nakalista
    -0.38
    Mikey
    -0.37
     Mikey
    -0.36
    OrEmpty
    -0.36
    POSITIVE LOGITS
     فريبيس
    0.47
     broadly
    0.44
    inter
    0.43
     Erkenntnis
    0.42
    GeneratedCode
    0.42
    Földrajzportál
    0.41
    sidenav
    0.41
    ốp
    0.41
     intellectual
    0.41
    int
    0.41
    Activations Density 1.487%

    No Known Activations