© 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-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 4141
    Prev
    Next
    INDEX
    Explanations

    references to emotional expressions or sentiments in conversations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OGND
    -0.59
     splendour
    -0.54
     rangi
    -0.54
     TextAppearance
    -0.52
     delicacies
    -0.52
     Specimen
    -0.51
     Signature
    -0.51
     portico
    -0.51
     Assay
    -0.50
     Exhibition
    -0.50
    POSITIVE LOGITS
     yeah
    1.20
     Yeah
    1.15
     Honestly
    1.14
     Maybe
    1.13
     Nope
    1.13
     Actually
    1.04
     maybe
    1.01
    yeah
    1.01
     nope
    1.00
    Maybe
    1.00
    Activations Density 0.305%

    No Known Activations