© 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. 8879
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to regulatory and planning processes

    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
     somebody
    -0.52
     davvero
    -0.50
     weirdly
    -0.49
     something
    -0.47
     newbies
    -0.46
     nobody
    -0.45
    AddTagHelper
    -0.45
     selfies
    -0.45
     paink
    -0.45
     maths
    -0.45
    POSITIVE LOGITS
     pursuant
    0.66
     Pemerintah
    0.59
     maintained
    0.52
     precluded
    0.52
     jurisdictional
    0.50
     hierzu
    0.50
     Pursuant
    0.50
     anticipated
    0.49
     withdrew
    0.49
     consistent
    0.48
    Activations Density 1.314%

    No Known Activations