© 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. 2-GEMMASCOPE-RES-16K
    6. 8720
    Prev
    Next
    INDEX
    Explanations

    assertions and confirmations in legal or formal statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Biografia
    -0.50
     Lawton
    -0.47
    ktır
    -0.43
     BoxDecoration
    -0.43
     szóci
    -0.41
     مواليد
    -0.41
     altid
    -0.41
     Lengkap
    -0.40
    EDEFAULT
    -0.40
     externi
    -0.40
    POSITIVE LOGITS
     assert
    0.96
     asserting
    0.85
    assert
    0.85
     asserted
    0.84
     assertion
    0.81
     assertions
    0.80
     asserts
    0.73
     asser
    0.69
    httphttps
    0.62
     Asser
    0.60
    Activations Density 0.115%

    No Known Activations