© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 8164
    Prev
    Next
    INDEX
    Explanations

    phrases indicating expectations versus actual outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    phrases indicating something occurred in a manner that aligns with prior expectations or predictions.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    出版年
    -0.53
     ujednoznacz
    -0.50
    UVWXYZ
    -0.50
    ſelves
    -0.49
    MENAFN
    -0.48
    AnimationsModule
    -0.47
     
    -0.47
    ſelf
    -0.47
     myſelf
    -0.46
    ResumeLayout
    -0.45
    POSITIVE LOGITS
     expected
    3.22
    expected
    2.83
     Expected
    2.70
    Expected
    2.69
     EXPECT
    2.42
     expect
    2.36
     expectation
    2.30
     expectations
    2.23
     expecting
    2.23
     anticipated
    2.17
    Activations Density 0.954%

    No Known Activations