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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 31-GEMMASCOPE-RES-16K
    6. 1026
    Prev
    Next
    INDEX
    Explanations

    expressions and sentiments related to affection and preference

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

    expressions of affection or enjoyment toward people, objects, or experiences.

    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
    IntoConstraints
    -0.51
     gyhoeddwyd
    -0.49
     giusti
    -0.48
    VersionUID
    -0.47
    Werdegang
    -0.47
    PagerAdapter
    -0.46
     uſ
    -0.45
     onOptions
    -0.45
     poveznice
    -0.44
     neceſſ
    -0.42
    POSITIVE LOGITS
     immensely
    0.87
     dearly
    0.81
     especially
    0.69
     enormously
    0.63
    especially
    0.63
     wholeheartedly
    0.62
     passionately
    0.60
     tremendously
    0.57
     особенно
    0.57
     deeply
    0.56
    Activations Density 0.214%

    No Known Activations