© 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. 16-GEMMASCOPE-RES-16K
    11. 4432
    Prev
    Next
    INDEX
    Explanations

    sentiments related to relationships and emotional complexities

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

    followed by prepositions/conjunctions

    np_acts-logits-general · gemini-2.0-flash

    grammatical connectors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     freilich
    -1.13
     offenbar
    -1.04
     ―――――
    -1.01
    Herzliche
    -0.96
    ]),
    -0.86
     auffi
    -0.85
     guère
    -0.84
     ་་
    -0.83
     (;;)
    -0.83
     '*':
    -0.83
    POSITIVE LOGITS
     alot
    0.86
     aswell
    0.82
     diatas
    0.79
    慢慢的
    0.79
    非常的
    0.76
     disini
    0.75
     данного
    0.75
     navidad
    0.74
     anyways
    0.74
     I
    0.70
    Activations Density 2.881%

    No Known Activations