© 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-2-9B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 2167
    Prev
    Next
    INDEX
    Explanations

    references to government agencies and organizations related to health and safety

    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
     kasarigan
    -0.64
     ujednoznacz
    -0.58
    RegressionTest
    -0.55
     ExecuteAsync
    -0.54
     وتسجيلات
    -0.52
    IsMutable
    -0.52
    nodoc
    -0.52
    قایناقلار
    -0.51
    ExtendWith
    -0.50
    contentLoaded
    -0.49
    POSITIVE LOGITS
     tarafından
    0.43
     officials
    0.43
     spokeswoman
    0.42
     setempat
    0.41
     Authorities
    0.41
     Administration
    0.40
     Officials
    0.40
    CodeAnalysis
    0.40
     []),
    0.39
     administration
    0.38
    Activations Density 0.600%

    No Known Activations