© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 14875
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and indicators of inclusion or lists

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

    Text following colons

    np_acts-logits-general · gemini-2.0-flash

    colon followed by one or if

    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
    出版年
    -0.79
     Савезне
    -0.77
    <bos>
    -0.71
    ngrx
    -0.66
     мәкалә
    -0.64
     للمعارف
    -0.61
    GHIJKLM
    -0.60
     Wikimedijinoj
    -0.60
    NSNotification
    -0.58
     estimés
    -0.58
    POSITIVE LOGITS
    ↵↵
    1.88
    ↵
    0.95
    ↵↵↵
    0.89
    ↵↵↵↵
    0.83
    ():
    0.79
    <eos>
    0.76
    ↵↵↵↵↵
    0.72
    ↵↵↵↵↵↵↵
    0.64
    ↵↵↵↵↵↵
    0.62
    :-
    0.61
    Activations Density 0.211%

    No Known Activations