© 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. 21-GEMMASCOPE-RES-16K
    6. 12759
    Prev
    Next
    INDEX
    Explanations

    elements related to emotional or expressive content in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    \{\\
    -0.53
    StoryboardSegue
    -0.52
    存于互联网档案馆
    -0.49
    ambilan
    -0.46
    AddTagHelper
    -0.46
    aitlin
    -0.46
    )?;
    -0.44
    eadilan
    -0.44
    __":
    -0.44
    těte
    -0.43
    POSITIVE LOGITS
     emoji
    1.18
     emoticon
    1.08
     emojis
    1.04
     Emo
    1.02
     emo
    0.97
    emoji
    0.94
    Emo
    0.94
     Emoji
    0.93
    emo
    0.87
     smiley
    0.85
    Activations Density 0.211%

    No Known Activations