© 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-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 2852
    Prev
    Next
    INDEX
    Explanations

    references to or expressions of emotional connection and support

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

    Followed by "copy" or "money"

    np_acts-logits-general · gemini-2.0-flash

    technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bagi
    -0.57
    对
    -0.56
    對
    -0.53
     supporting
    -0.48
     among
    -0.48
    对于
    -0.48
    對於
    -0.47
    给
    -0.47
     auprès
    -0.45
    ius
    -0.45
    POSITIVE LOGITS
    ValueStyle
    0.94
     CreateTagHelper
    0.92
    
    0.91
     betweenstory
    0.89
    +#+#
    0.88
    InjectAttribute
    0.87
     beginnetje
    0.87
    httphttps
    0.84
    InputBorder
    0.82
    COUVER
    0.82
    Activations Density 0.316%

    No Known Activations