© 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. 39-GEMMASCOPE-RES-16K
    6. 4770
    Prev
    Next
    INDEX
    Explanations

    legal terms related to sentencing and justice

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     burbuja
    -0.44
    queryInterface
    -0.43
     nakalista
    -0.43
     ditangkap
    -0.42
     ayudará
    -0.41
     enriquec
    -0.40
     arrep
    -0.40
     integran
    -0.39
     mejora
    -0.38
     tué
    -0.37
    POSITIVE LOGITS
     imposed
    1.28
     inflicted
    1.17
     impose
    1.05
     imposition
    1.00
     heaped
    0.99
    imposed
    0.96
     inflict
    0.94
     imposes
    0.89
     levied
    0.88
     imposing
    0.88
    Activations Density 0.859%

    No Known Activations