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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 73646
    Prev
    Next
    INDEX
    Explanations

    expressions of pressure and anxiety in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ValueStyle
    -0.62
     Exacts
    -0.54
     يتيمه
    -0.52
     الرياضيه
    -0.47
    MessageTagHelper
    -0.46
    oredCriteria
    -0.45
    يكب
    -0.44
    Bibliograf
    -0.42
     ISNI
    -0.42
     houſe
    -0.42
    POSITIVE LOGITS
     easily
    0.54
    easily
    0.53
     легко
    0.52
    SequentialGroup
    0.50
     weak
    0.49
     cowardly
    0.49
     succumb
    0.48
    Easily
    0.47
     cowardice
    0.47
     surrendering
    0.47
    Activations Density 0.082%

    No Known Activations