© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 3088
    Prev
    Next
    INDEX
    Explanations

    instances of the word "cry" and its contextual associations related to emotional expression

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/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.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mijne
    -0.70
     zoude
    -0.67
     zijne
    -0.67
     Italij
    -0.65
     nôtre
    -0.62
     voordelen
    -0.62
     moeite
    -0.61
     goederen
    -0.60
     étoit
    -0.59
     pouvoit
    -0.57
    POSITIVE LOGITS
     conscience
    0.63
     blog
    0.58
     listeners
    0.58
     franchise
    0.56
     bot
    0.55
     podcast
    0.55
     readers
    0.53
     FIM
    0.53
     п
    0.53
     correspond
    0.52
    Activations Density 0.478%

    No Known Activations