Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 7533
    Prev
    Next
    INDEX
    Explanations

    phrases related to expectations or predictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     privada
    -0.38
     aislado
    -0.37
     individuales
    -0.37
    private
    -0.37
     aislada
    -0.36
    后再
    -0.36
     caneta
    -0.36
     Waterman
    -0.36
    borderWidth
    -0.36
     noires
    -0.35
    POSITIVE LOGITS
     Expect
    1.34
    expect
    1.28
    Expect
    1.27
     expect
    1.25
     EXPECT
    1.23
     expectancy
    1.15
     expectation
    1.13
     Expectation
    1.09
     Expectations
    1.09
    Expectations
    1.07
    Activations Density 0.172%

    No Known Activations